Tools Reference

Morphic MCP registers 161 tools, organised into 24 groups. Generated from morphic-mcp v0.4.0. Read Tools Guide first for conventions that apply across tools — the bulk-tool contract, the error envelope, object-type slugs, and worked recipes.

The Paid Add-ons group is not advertised by default. Its tools are hidden unless the operator sets MCP_TOOL_GROUPS to include addons, or the connection URL asks for them with ?tools=addons. Every other group is on by default. See Tool Groups.

Groups

Group	`id`	Tools	Default	Purpose
Context	`context`	2	on	Start here for questions. Compacted briefs on the current state of any record, of any object type the workspace has defined, plus semantic recall over the workspace’s indexed history. Cheaper and better-grounded than reading raw records; drill into Records, Activities or Memory only when this falls short.
Schema	`schema`	2	on	Discover the workspace’s record types and their field definitions — the starting point for any CRM read or write.
Records	`entities`	18	on	Create, read, update, link, archive and bulk-edit CRM records of any type — companies, people, deals and custom objects.
Activities	`activities`	12	on	Log and manage the timeline attached to records: calls, emails, meetings, tasks and custom activity types.
Notes	`notes`	6	on	Write and manage free-form notes attached to CRM records, individually or in bulk.
Knowledge Base	`kb`	6	on	Search, read and author knowledge-base documents, and pull the workspace’s overall context summary.
Wiki	`wiki`	5	on	Read and edit the agent-maintained wiki — durable, section-addressable pages the workspace’s agents write to.
Memory	`memory`	3	on	Semantic recall over the workspace’s stored knowledge and attachments, plus writing new memories back.
Calendar	`calendar`	6	on	Read and manage calendar events on the user’s connected calendar, and check connection status.
Meetings	`meetings`	7	on	Meeting recordings and recaps: transcripts, follow-ups, record linking, and dispatching the note-taking bot.
Automations	`automations`	11	on	Author, publish, run and inspect workflow automations, including their triggers and run history.
Revenue Intelligence	`revenue-intelligence`	18	on	Run the LLM-backed GTM analyses: pre/post-meeting packs, deal-risk scans, pipeline narration, executive digests and CRM hygiene.
External CRM sync	`connectors`	8	on	Push field changes on Morphic records out to a connected external CRM (e.g. HubSpot) and mirror the same change locally, and review records that changed on both sides at once.
Amplemarket	`amplemarket`	3	on	Use the asking user’s own Amplemarket seat — check their connection, discover which of the 9 tool categories their plan includes, and run one. Per person, not per workspace.
TinyFish	`tinyfish`	7	on	Search the web, read pages, and drive a real browser to complete website tasks, using the asking user’s own TinyFish account. Search and page reads are free; browser automation is metered against that user’s wallet. Per person, not per workspace.
Meeting notetakers	`notetakers`	7	on	Search and read the asking user’s meeting transcripts, summaries and action items across every notetaker they have connected (Granola, Fireflies, Fathom, Otter, Circleback, Read.ai, Sybill, Plaud, tl;dv, Gong). Read-only, and per person rather than per workspace — a connected teammate does not let this user read anything.
Apollo	`apollo`	9	on	Search Apollo’s global prospect database, enrich people and companies, log calls and tasks that push into Apollo, and enroll contacts in an existing Apollo sequence. Workspace-wide, connected once via Composio.
Clay	`clay`	8	on	Search Clay’s GTM database, run Clay routines and check their results, read Clay Tables data, and check the workspace’s Clay credit balance. Workspace-wide, one API key for the whole team — connected directly to Clay’s Developer API, not via Composio.
Clay (MCP)	`clay_mcp`	6	on	Prospect and enrich companies and contacts via Clay’s own hosted MCP server, using the asking user’s own OAuth connection. Per person, not per workspace — unlike the Clay group above, which is one shared workspace API key.
Stage Requirements	`stage-requirements`	6	on	Discover and propose deterministic entry requirements for a CRM pipeline stage — read the connected pipeline’s stages, existing requirements and revision history, then propose a new or updated requirement for the user to confirm on a review card.
Workspace	`workspace`	4	on	Identify the current user, list workspace members, and read workspace-level configuration.
Task Suggestions	`tasks`	2	on	Review and accept the agent-generated task suggestions queued for the workspace.
Web Search	`search`	1	on	Search the public web and fetch page content for research that goes beyond workspace data.
Paid Add-ons	`addons`	3	opt-in	Marketplace add-ons billed separately and usable only once installed for the workspace: Parallel Search, Flint and AgentMail.
Diagnostics	(ungrouped)	1	always	Connection smoke test; registered on every profile, however narrow.

Diagnostics

Always registered, in every group profile — use it to confirm a connection before debugging anything else.

`ping`

Ping · read-only Test the MCP server connection and confirm env is configured. Parameters: none

Context

Start here for questions. Compacted briefs on the current state of any record, of any object type the workspace has defined, plus semantic recall over the workspace’s indexed history. Cheaper and better-grounded than reading raw records; drill into Records, Activities or Memory only when this falls short. Group id: context.

`ask_context`

Ask Context · read-only Do not use this tool to resolve a task assignee. When the user asks to create / assign / add / make a task, call list_workspace_members or get_current_user FIRST — CRM people are not assignees; only look up CRM records if they clearly want the task linked to a company, deal, or contact. Otherwise START HERE for any question about this workspace — its records, and also what people have SAID or DONE: past conversations, Slack and Telegram messages, emails, meetings and call transcripts. Every message the workspace has connected is indexed and searchable through this tool. You DO have access to conversation and channel history: it reaches you through this tool, not through Slack’s or Gmail’s own APIs. Never tell the user you cannot search past messages or channel history — call this first and answer from what it returns. Use it even when the question names no record at all (“did anyone mention the staging box?”, “what did we say about pricing last week?”) — the semantic layer answers those. Works across EVERY object type — the workspace defines its own, so this is not limited to any fixed set of record kinds, and you do not need to know the type, its fields or its id in advance. Pass the user’s question verbatim: this resolves which records it is about and returns, for each, a compacted brief of the current state (typically what is going on, the next step, outstanding commitments and anything of concern) plus a semantic recall over the workspace’s indexed history — in one call. Prefer this over search_entities, list_activities and morphic_recall, which return raw, undigested data at higher cost; call those only when this tool’s next_steps says to. If contexts is empty, semantic is still a complete answer — Slack-only workspaces do not auto-create CRM records. Empty semantic too means nothing is indexed yet — say that, rather than claiming you lack access.

Parameter	Type	Required	Default	Description
`question`	string ≥ 1	Yes	—	The user’s question, verbatim. Do not pre-extract names — this resolves them.
`max_entities`	integer 1–5	—	`3`	Max records to return context for when the question touches several. Defaults to 3.
`include_graph`	boolean	—	`true`	Include the per-record relationship layer. Set false for the brief alone.

`get_context`

Get Context · read-only Get the compacted brief for ONE record you already have the id of, of ANY object type — the current state in prose (typically what is going on, the next step, outstanding commitments and anything of concern) plus a bounded relationship layer. Use this instead of get_entity when you want to know how the record is DOING rather than read its raw field values. If you only have a name or a question, call ask_context instead — it resolves the record for you.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	UUID of the record, of any object type

Schema

Discover the workspace’s record types and their field definitions — the starting point for any CRM read or write. Group id: schema.

`list_entity_types`

List Entity Types · read-only List all CRM entity types (object types) in this workspace — e.g. people, companies, deals, plus any custom types — returning slug, name and base_type only, not their fields. Call this first to discover valid slugs, then get_entity_type_schema for one type’s attribute slugs before reading or writing entities.

Parameter	Type	Required	Default	Description
`page`	integer ≥ 1	—	`1`	1-based page number. Defaults to 1 (first page).
`page_size`	integer 1–100	—	`50`	Items per page, 1–100. Defaults to 50, which covers most workspaces in a single call.

`get_entity_type_schema`

Get Entity Type Schema · read-only Get the attribute schema (field slugs, names, types, required/relation flags, options) for ONE entity type. Call this after list_entity_types and BEFORE create_entity/update_entity/set_entity_field to learn the exact field slugs.

Parameter	Type	Required	Default	Description
`object_type_slug`	string ≥ 1	Yes	—	Entity type slug, e.g. ‘people’, ‘companies’, ‘deals’

Records

Create, read, update, link, archive and bulk-edit CRM records of any type — companies, people, deals and custom objects. Group id: entities.

`present_crm_card`

Present CRM Card (deprecated) · read-only DEPRECATED — do not use. Web chat presentation is owned by the assistant presentation layer (presentation intent → builders → envelope), not MCP. This shim remains for older agents only and does not write to CRM.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	CRM entity UUID (Open target)
`object_type_slug`	string ≥ 1	Yes	—	Object type slug, e.g. companies, people, deals
`title`	string ≥ 1	Yes	—	Display name for the card header
`subtitle`	string	—	—	Optional one-line context, e.g. ‘Company · Qualified’
`highlights`	object[]	Yes	—	3–8 human-readable label/value rows for the card body
`related`	object[]	—	—	Optional related people/deals by name (never raw UUIDs), e.g. label ‘Team’, value ‘Atharva — Jr. Developer’

`list_entities`

List Entities · read-only List CRM entities by exact criteria — object type, archive state, specific ids, or field-level filter conditions — returning paginated records with a flat fields dict each. Use this whenever you know the literal value you’re matching on; for conceptual or fuzzy ‘find something about X’ lookups use search_entities (vector search) instead, because search here is a literal substring match only.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	—	—	Object type slug, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`search`	string	—	—	EXACT case-insensitive SUBSTRING match across entity fields — not semantic. ‘acme’ matches ‘Acme Corp’; ‘enterprise software vendor’ matches nothing unless that literal string is stored. For meaning-based lookup use search_entities.
`is_archived`	boolean	—	—	Filter archived entities (default: false)
`entity_ids`	UUID[]	—	—	Restrict results to these specific entity UUIDs
`filters`	object	—	—	Field-level conditions keyed by attribute slug, e.g. { “deal_value”: { “operator”: “greater_than”, “value”: 10000 }, “stage”: { “operator”: “is”, “value”: “negotiation” } }. Use get_entity_type_schema first to find valid slugs.
`sort_by`	string	—	—	Sort expression, e.g. ‘created_at:desc’ or ‘deal_value:asc’
`page`	integer ≥ 1	—	`1`	1-based page number. Defaults to 1 (first page).
`page_size`	integer 1–100	—	`25`	Items per page, 1–100. Defaults to 25; raise it rather than paging repeatedly.

`get_entity`

Get Entity · read-only Get one CRM entity by id with its full fields dict; its relations are STUBS only (id + title), not the related records’ fields. Use this when you only need this record — if you need any field of a related record, call get_entity_with_relations once instead of looping get_entity over the relation stubs. This returns raw field VALUES — if you want to know how the record is DOING (status, next step, risks, recent activity), call get_context or ask_context instead.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID, e.g. from list_entities or search_entities

`get_entity_with_relations`

Get Entity With Relations · read-only Get an entity plus the FULL record (fields, not just the id/title stubs get_entity returns) of every entity it’s related to, in one call. Use this whenever the question touches related records — a deal’s contacts, a company’s people — and use get_entity only when the related records’ fields are genuinely irrelevant.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID whose record and related records should be returned

`create_entity`

Create Entity Create a new CRM entity. Provide the object type slug (e.g. ‘people’, ‘companies’) and a fields dict with attribute values. Use list_entity_types to discover available types and get_entity_type_schema for their attribute slugs.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	Yes	—	Object type slug, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`fields`	object	Yes	—	Flat dict of attribute slug → value, e.g. { name: ‘Alice’, email: ‘alice@acme.com’ }

`update_entity`

Update Entity · idempotent Update one or more fields on an existing entity. Only provided fields are changed (PATCH semantics).

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID to update
`fields`	object	Yes	—	Flat dict of attribute slug → new value. Only include fields to change.

`set_entity_field`

Set Entity Field · idempotent Set exactly one field on an entity by attribute slug. Prefer this when changing a single value; use update_entity when writing two or more fields in one round-trip.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID
`slug`	string	Yes	—	Attribute slug, e.g. ‘email’, ‘phone’, ‘stage’. Get valid slugs from get_entity_type_schema.
`value`	string \| number \| boolean \| any[] \| object	Yes	—	New value for the field — required. Any JSON type matching the attribute: string, number, boolean, array, object, or null to clear the field. Must be supplied explicitly; there is no implicit default.

`link_entities`

Link Entities · idempotent Create a relation between two entities, e.g. link a person to a company or a deal to a contact.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Source entity UUID
`attribute_slug`	string	Yes	—	Relation attribute slug on the source entity, e.g. ‘company’, ‘contacts’
`target_entity_id`	UUID	Yes	—	Target entity UUID to link to

`search_entities`

Search Entities · read-only Semantic / natural-language search across all indexed CRM RECORDS ONLY — every object type the workspace has defined, standard or custom — using vector recall — matches on MEANING, so ‘follow up with Alice about pricing’ can hit records containing none of those words. It does not see Knowledge Base docs, the agent wiki, or memory. NOT a first resort for “how is X doing” style questions: call ask_context first — it resolves the record from the question and returns a pre-compacted brief. Use this to LOCATE records when ask_context resolved nothing, or when you need a ranked list rather than one record’s story. Never use this to resolve a task assignee — that is list_workspace_members / get_current_user. One of four separate retrieval stores: use search_kb_documents for human-authored Knowledge Base docs, wiki_search for agent-distilled team knowledge, and morphic_recall for cross-session memory about this user/workspace. Use it for fuzzy or conceptual lookups; when you know the literal value to match (an email, a name, a stage, an id) use list_entities with search or filters, which is exact and cheaper. Returns entity UUIDs + relevance scores — call get_entity to hydrate full records.

Parameter	Type	Required	Default	Description
`query`	string ≥ 1	Yes	—	Natural language search query — a phrase or question, not a keyword
`object_type_slug`	string	—	—	Object type slug, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`limit`	integer 1–50	—	`10`	Max results to return

`pipeline_overview`

Pipeline Overview · read-only High-level pipeline view of CRM entities. For the usual deal pipeline (object_type_slug=deal, group_by_slug=stage) this runs run_pipeline_narration under the hood — same stage/value grouping plus a narrative artifact you should present as a chat card. On web chat, after success call present with type artifact_generic and the returned title/summary/body_markdown (kind pipeline_narration) — do not only summarize in prose or paste a markdown table. For a custom object_type / group_by / value_slug aggregation (not the default deal pipeline), this returns grouped counts/sums only (no card) — scan up to 5000 entities and check truncated on the response.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	Yes	—	Object type slug, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing. Typically ‘deals’ for pipeline questions.
`group_by_slug`	string	Yes	—	Attribute slug to group by, e.g. ‘stage’ or ‘status’
`value_slug`	string	—	—	Optional numeric attribute slug to sum per group, e.g. ‘amount’
`is_archived`	boolean	—	`false`	Include archived entities (default: active only)

`archive_entity`

Archive Entity · idempotent Archive a CRM entity so it no longer appears in default listings. Reversible — use unarchive=true to restore.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID to archive
`unarchive`	boolean	—	`false`	Set true to unarchive instead

`delete_entity`

Delete Entity · destructive · idempotent Permanently delete a CRM record and its links to other records. Field values stored on the record are removed with it. Meetings, emails, and other activity are kept and marked as belonging to a deleted record; they will no longer appear on a record page. Archive the record instead if you need to keep it and its history. This cannot be undone.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Entity UUID to delete

`bulk_update_entities`

Bulk Update Entities · idempotent Apply the same field updates to up to 200 CRM entities in one call, e.g. moving a batch of deals to a new stage. All entities get the same fields dict — for per-entity different values, call update_entity individually instead. Returns per-id success/failure so partial failures don’t block the rest.

Parameter	Type	Required	Default	Description
`entity_ids`	UUID[]	Yes	—	Entity UUIDs to update
`fields`	object	Yes	—	Flat dict of attribute slug → new value, applied to every entity

`bulk_archive_entities`

Bulk Archive Entities · idempotent Archive (or unarchive) up to 200 CRM entities in one call. Reversible — use unarchive=true to restore.

Parameter	Type	Required	Default	Description
`entity_ids`	UUID[]	Yes	—	Entity UUIDs to archive
`unarchive`	boolean	—	`false`	Set true to unarchive instead

`bulk_delete_entities`

Bulk Delete Entities · destructive · idempotent Permanently delete up to 200 CRM entities in one call. This cannot easily be undone — prefer bulk_archive_entities when in doubt.

Parameter	Type	Required	Default	Description
`entity_ids`	UUID[]	Yes	—	Entity UUIDs to delete

`unlink_entities`

Unlink Entities · idempotent Remove a relation between two entities, e.g. unlink a person from a company.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	Source entity UUID
`attribute_slug`	string	Yes	—	Relation attribute slug on the source entity, e.g. ‘company’, ‘contacts’
`target_entity_id`	UUID	Yes	—	Target entity UUID to unlink

`bulk_link_entities`

Bulk Link Entities · idempotent Create up to 200 entity relations in one call, e.g. linking a batch of contacts to the same company. Returns per-operation success/failure so one bad pair doesn’t block the rest.

Parameter	Type	Required	Default	Description
`operations`	object[]	Yes	—	1–200 link operations, each an independent (source entity, relation attribute slug, target entity) triple — they need not share a source or an attribute. Applied individually with per-operation success/failure reported, so one bad pair does not abort the batch.

`bulk_unlink_entities`

Bulk Unlink Entities · idempotent Remove up to 200 entity relations in one call. Removes only the links — the entities themselves are untouched; use bulk_archive_entities or bulk_delete_entities to act on the records.

Parameter	Type	Required	Default	Description
`operations`	object[]	Yes	—	1–200 unlink operations, each an independent (source entity, relation attribute slug, target entity) triple identifying the relation to remove. Applied individually with per-operation success/failure reported, so one bad pair does not abort the batch.

Activities

Log and manage the timeline attached to records: calls, emails, meetings, tasks and custom activity types. Group id: activities.

`list_activities`

List Activities · read-only List the activity/task timeline, optionally scoped to one entity, type, status, or assignee — this is the unified store for both logged interactions and actionable tasks. For ‘my tasks’ / ‘tasks assigned to me’: call get_current_user, then list_activities with activity_type=‘task’ and assignee_user_id set to that user_id (do NOT page unfiltered activities and scan for a name). Use get_activity when you already have an id, and list_notes for standalone notes. On web chat, after success call present with type task: for lists use body {label, tasks:[{task_id, title, status?, due_date?, assignees?:[{name}]}]} (map subject→title, user_name→assignees); for a single task use {title, task_id?, …}. Do not dump a markdown task/priority bullet list.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	—	—	Filter by linked entity UUID
`entity_type`	string	—	—	Object type slug of the linked CRM record (‘Linked to’), e.g. ‘people’, ‘companies’, ‘deals’. This is NOT the assignee. Workspaces can define custom types — call list_entity_types rather than guessing.
`activity_type`	string	—	—	Filter by type: ‘email’, ‘meeting’, ‘call’, ‘task’, ‘note’, ‘stage_change’, ‘payment’ (a customer payment from their Stripe account), ‘lemlist_activity’ (an outbound-campaign reply / bounce / unsubscribe).
`status`	string	—	—	Workspace task-status slug only (e.g. ‘not_started’, ‘in_progress’, ‘completed’, ‘cancelled’). NOT enumerable here: statuses are workspace-configurable, so call list_task_statuses for this workspace’s exact slugs — never invent values like ‘pending’.
`assignee_user_id`	UUID	—	—	Filter to activities/tasks assigned to this workspace member user_id (crm_activities.user_id). For ‘my tasks’, pass get_current_user’s user_id.
`page`	integer ≥ 1	—	`1`	1-based page number. Defaults to 1 (first page).
`page_size`	integer 1–100	—	`25`	Items per page, 1–100. Defaults to 25; raise it rather than paging repeatedly.

`get_activity`

Get Activity · read-only Fetch one activity or task by id, including description, status, priority, assignee, due date and parent/child task links. Use it to inspect a single record you already have an id for — to find records in the first place, use list_activities. On web chat, after success call present with type task: for lists use body {label, tasks:[{task_id, title, status?, due_date?, assignees?:[{name}]}]} (map subject→title, user_name→assignees); for a single task use {title, task_id?, …}. Do not dump a markdown task/priority bullet list.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity UUID, e.g. from list_activities

`create_activity`

Create Activity Log a new activity or create a task. Set activity_type to ‘task’ for actionable items with due dates. For create / assign / add / make / reassign a task: resolve the assignee FIRST with list_workspace_members (named teammate) or get_current_user (‘me’ / ‘myself’). Do NOT call ask_context or search_entities to identify who to assign — CRM people/contacts are never assignees. assignee_user_id is a workspace member user_id. entity_id/entity_type is a separate ‘Linked to’ CRM association: set it only when the user clearly wants the task on a record (‘for Acme’, ‘on this deal’, ‘link this to the Alice contact’). A name in ‘assign to X’ is an assignee, not a Linked-to record. To unlink a record, pass entity_id and entity_type both null on update_activity. Use ‘email’, ‘call’, ‘meeting’ to log completed interactions, and activity_type=‘note’ for a note that must appear on the timeline in chronological order alongside them — use create_note instead for a standalone, editable, pinnable note that lives in the entity’s notes panel rather than the timeline. Pass parent_task_id to create a sub-task. For task status, use list_task_statuses — only workspace slugs are accepted. On web chat, after success call present with type task: for lists use body {label, tasks:[{task_id, title, status?, due_date?, assignees?:[{name}]}]} (map subject→title, user_name→assignees); for a single task use {title, task_id?, …}. Do not dump a markdown task/priority bullet list.

Parameter	Type	Required	Default	Description
`activity_type`	`task` \| `email` \| `call` \| `meeting` \| `note` \| `stage_change`	Yes	—	‘task’ for actionable work with a due date/assignee; ‘email’, ‘call’, ‘meeting’ to log a completed interaction; ‘note’ for a timeline note; ‘stage_change’ for a pipeline movement record.
`subject`	string	—	—	Short summary / task title
`description`	string	—	—	Full description or notes
`entity_id`	UUID	—	—	UUID of the CRM record to link (‘Linked to’). Omit unless the user clearly wants a record association — not for assignees.
`entity_type`	string	—	—	Object type slug of the linked CRM record (‘Linked to’), e.g. ‘people’, ‘companies’, ‘deals’. This is NOT the assignee. Workspaces can define custom types — call list_entity_types rather than guessing.
`due_date`	string	—	—	ISO8601 due date, e.g. ‘2026-06-15T10:00:00Z’
`priority`	`low` \| `medium` \| `high`	—	—	Task priority. One of ‘low’, ‘medium’, ‘high’.
`status`	string	—	—	Workspace task-status slug only (e.g. ‘not_started’, ‘in_progress’, ‘completed’, ‘cancelled’). NOT enumerable here: statuses are workspace-configurable, so call list_task_statuses for this workspace’s exact slugs — never invent values like ‘pending’.
`assignee_user_id`	UUID	—	—	Workspace member user UUID to assign this task to (stored as user_id). Never a CRM person entity id.
`parent_task_id`	UUID	—	—	Parent task UUID — set to create this as a sub-task
`duration_minutes`	integer ≥ 0	—	—	Duration in minutes, e.g. for a call or meeting

`update_activity`

Update Activity · idempotent Update fields on an existing activity or task. Only provided fields are changed. For create / assign / add / make / reassign a task: resolve the assignee FIRST with list_workspace_members (named teammate) or get_current_user (‘me’ / ‘myself’). Do NOT call ask_context or search_entities to identify who to assign — CRM people/contacts are never assignees. assignee_user_id is a workspace member user_id. entity_id/entity_type is a separate ‘Linked to’ CRM association: set it only when the user clearly wants the task on a record (‘for Acme’, ‘on this deal’, ‘link this to the Alice contact’). A name in ‘assign to X’ is an assignee, not a Linked-to record. To unlink a record, pass entity_id and entity_type both null on update_activity. For status, use only slugs from list_task_statuses (e.g. in_progress — not pending). Pass assignee_user_id to (re)assign, or null to unassign. Pass entity_id and entity_type together to change the Linked-to record, or both null to unlink. Use archive_activity/unarchive_activity/delete_activity for those lifecycle changes instead of this tool.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity UUID to update
`subject`	string	—	—	New short summary / task title
`description`	string	—	—	New full description or notes (replaces the existing text)
`status`	string	—	—	Workspace task-status slug only (e.g. ‘not_started’, ‘in_progress’, ‘completed’, ‘cancelled’). NOT enumerable here: statuses are workspace-configurable, so call list_task_statuses for this workspace’s exact slugs — never invent values like ‘pending’.
`priority`	`low` \| `medium` \| `high`	—	—	Task priority. One of ‘low’, ‘medium’, ‘high’.
`due_date`	string	—	—	ISO8601 datetime
`outcome`	string	—	—	Outcome or result notes
`assignee_user_id`	UUID	—	—	Workspace member user UUID to assign; pass null to unassign. Never a CRM person entity id.
`entity_id`	UUID	—	—	CRM record UUID to link (‘Linked to’). Pass null together with entity_type null to unlink. Not the assignee.
`entity_type`	string	—	—	Object type slug of the linked CRM record. Pass null together with entity_id null to unlink.
`parent_task_id`	UUID	—	—	Move this activity under a different parent task
`duration_minutes`	integer ≥ 0	—	—	Duration in minutes, e.g. for a call or meeting

`archive_activity`

Archive Activity · idempotent Archive an activity or task so it’s hidden from active views. Reversible with unarchive_activity. Cascades to sub-tasks.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity UUID to archive

`unarchive_activity`

Unarchive Activity · idempotent Restore an archived activity or task to active views. Cascades to sub-tasks.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity UUID to unarchive

`delete_activity`

Delete Activity · destructive · idempotent Soft-delete an activity or task. This cannot easily be undone — prefer archive_activity when in doubt.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity UUID to delete

`bulk_create_activities`

Bulk Create Activities Log up to 200 activities or tasks in one call — e.g. logging the same call outcome across several entities, or creating a batch of follow-up tasks. Returns per-item success/failure and the created ids. For create / assign / add / make / reassign a task: resolve the assignee FIRST with list_workspace_members (named teammate) or get_current_user (‘me’ / ‘myself’). Do NOT call ask_context or search_entities to identify who to assign — CRM people/contacts are never assignees. assignee_user_id is a workspace member user_id. entity_id/entity_type is a separate ‘Linked to’ CRM association: set it only when the user clearly wants the task on a record (‘for Acme’, ‘on this deal’, ‘link this to the Alice contact’). A name in ‘assign to X’ is an assignee, not a Linked-to record. To unlink a record, pass entity_id and entity_type both null on update_activity.

Parameter	Type	Required	Default	Description
`items`	object[]	Yes	—	1–200 activities to create, each fully independent — one item per activity, with its own type, linked entity, assignee and due date. Items are applied individually and the response reports per-item success/failure, so a single bad item does not abort the batch.

`bulk_update_activities`

Bulk Update Activities · idempotent Apply the same field updates to up to 200 activities/tasks in one call, e.g. reassigning a batch of tasks. All activities get the same values — for per-activity different values, call update_activity individually instead. Returns per-id success/failure so partial failures don’t block the rest.

Parameter	Type	Required	Default	Description
`activity_ids`	UUID[]	Yes	—	Activity UUIDs to update
`subject`	string	—	—	New subject applied to every listed activity
`status`	string	—	—	Workspace task-status slug only (e.g. ‘not_started’, ‘in_progress’, ‘completed’, ‘cancelled’). NOT enumerable here: statuses are workspace-configurable, so call list_task_statuses for this workspace’s exact slugs — never invent values like ‘pending’.
`priority`	`low` \| `medium` \| `high`	—	—	Task priority. One of ‘low’, ‘medium’, ‘high’.
`due_date`	string	—	—	ISO8601 datetime
`assignee_user_id`	UUID	—	—	User UUID to assign every activity to

`bulk_archive_activities`

Bulk Archive Activities · idempotent Archive (or unarchive) up to 200 activities/tasks in one call. Reversible — use unarchive=true to restore.

Parameter	Type	Required	Default	Description
`activity_ids`	UUID[]	Yes	—	Activity UUIDs to archive
`unarchive`	boolean	—	`false`	Set true to unarchive instead

`bulk_delete_activities`

Bulk Delete Activities · destructive · idempotent Soft-delete up to 200 activities/tasks in one call. Prefer bulk_archive_activities when in doubt.

Parameter	Type	Required	Default	Description
`activity_ids`	UUID[]	Yes	—	Activity UUIDs to delete

`complete_task`

Complete Task · idempotent Mark a task or activity as completed. Works for any task in the workspace (not only ones assigned to the caller). Prefer this over update_activity for completion.

Parameter	Type	Required	Default	Description
`activity_id`	UUID	Yes	—	Activity / task UUID to complete

Notes

Write and manage free-form notes attached to CRM records, individually or in bulk. Group id: notes.

`list_notes`

List Notes · read-only List standalone notes (title, body, pinned state), newest first, optionally scoped to the entity they’re attached to. Use this to read what people have written up about a record; use list_activities instead for the chronological interaction timeline, including activity_type=‘note’ entries, which do not appear here.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	—	—	Filter notes by linked entity UUID
`entity_type`	string	—	—	Object type slug of the entity, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`page`	integer ≥ 1	—	`1`	1-based page number. Defaults to 1 (first page).
`page_size`	integer 1–100	—	`25`	Items per page, 1–100. Defaults to 25; raise it rather than paging repeatedly.

`create_note`

Create Note Create a standalone note on a CRM entity — durable reference material (context, research, account background) that lives in the record’s notes panel and can later be edited or pinned via update_note. For something that happened at a point in time and belongs in the chronological timeline, call create_activity with activity_type=‘note’ (or ‘call’/‘email’/‘meeting’) instead.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	UUID of the entity to attach this note to
`entity_type`	string	Yes	—	Object type slug of the entity, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`body`	string ≥ 1	Yes	—	Note content (supports markdown)
`title`	string	—	—	Optional note title

`update_note`

Update Note · idempotent Edit an existing note in place — title, body, or pinned state; omitted fields are left untouched, and body REPLACES the previous text rather than appending. Use this to revise or pin a note; use create_note when the content belongs in a separate note.

Parameter	Type	Required	Default	Description
`note_id`	UUID	Yes	—	Note UUID to update
`body`	string ≥ 1	—	—	New note content (markdown). REPLACES the existing body — include prior text you want to keep.
`title`	string	—	—	New note title
`pinned`	boolean	—	—	true to pin the note to the top of the entity’s notes panel, false to unpin

`bulk_create_notes`

Bulk Create Notes Create up to 200 notes in one call, e.g. logging the same note across a list of entities. Returns per-item success/failure.

Parameter	Type	Required	Default	Description
`items`	object[]	Yes	—	1–200 notes to create, each independent — one item per note, with its own target entity and body (repeat the same body across items to log identical text on many entities). Items are applied individually with per-item success/failure reported, so one bad item does not abort the batch.

`bulk_delete_notes`

Bulk Delete Notes · destructive · idempotent PERMANENTLY delete up to 200 notes in one call. Notes have no archive state — unlike entities or activities there is nothing to restore, so confirm with the user before calling.

Parameter	Type	Required	Default	Description
`note_ids`	UUID[]	Yes	—	Note UUIDs to delete

`delete_note`

Delete Note · destructive · idempotent PERMANENTLY delete one note — notes have no archive state, so unlike archive_entity/archive_activity this is irreversible and there is no restore path. Prefer update_note to correct a note’s contents, and only delete when the user explicitly asks for removal.

Parameter	Type	Required	Default	Description
`note_id`	UUID	Yes	—	Note UUID to delete

Knowledge Base

Search, read and author knowledge-base documents, and pull the workspace’s overall context summary. Group id: kb.

`list_kb_documents`

List KB Documents · read-only Browse the team Knowledge Base tree. Without parent_id returns root-level items; set fetch_all=true to flatten every folder. Use this to see what exists; use search_kb_documents when you know what you’re looking for. LOSSY: each item’s content_markdown is truncated to a ~160-character excerpt and the BlockNote content field is removed entirely — call get_kb_document for a real body.

Parameter	Type	Required	Default	Description
`parent_id`	UUID	—	—	Parent folder UUID; omit for root
`fetch_all`	boolean	—	`false`	Return all docs across all hierarchy levels
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–100	—	`25`	Documents per page (1-100, default 25)

`search_kb_documents`

Search KB Documents · read-only Full-text search over the team KNOWLEDGE BASE ONLY — the human-authored docs, notes and playbooks in the KB UI. It does not see CRM records, the agent wiki, or memory. One of four separate retrieval stores: use search_entities for CRM records of any object type, wiki_search for agent-distilled team knowledge, and morphic_recall for cross-session memory about this user/workspace. Results carry ~160-character excerpts only — call get_kb_document for a full body.

Parameter	Type	Required	Default	Description
`q`	string ≥ 1	Yes	—	Search query
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–50	—	`10`	Results per page (1-50, default 10)

`get_kb_document`

Get KB Document · read-only Read one Knowledge Base document in full — untruncated content_markdown plus the BlockNote content body that the list/search tools strip. Call this after list_kb_documents or search_kb_documents when an excerpt isn’t enough to answer; it is the only KB tool that returns a complete body, so prefer the search tool first to find the right document id.

Parameter	Type	Required	Default	Description
`document_id`	UUID	Yes	—	KB document UUID

`create_kb_document`

Create KB Document Create a knowledge base document or folder, visible and editable by humans in the KB UI. This is the regular team Knowledge Base — NOT the Agent Wiki (use wiki_write for agent-maintained, read-only-for-humans pages instead).

Parameter	Type	Required	Default	Description
`title`	string 1–255	Yes	—	Document title
`type`	`page` \| `folder`	—	`"page"`	’folder’ has no content; ‘page’ does
`content_markdown`	string	—	—	Markdown content (pages only)
`parent_id`	UUID	—	—	Parent folder UUID; omit for root
`visibility`	`private` \| `public`	—	`"private"`	’private’ = workspace-internal; ‘public’ = shareable outside the workspace

`update_kb_document`

Update KB Document · idempotent Update a knowledge base document’s title, content, visibility, or parent folder. Only provided fields change, but content_markdown REPLACES the whole body — read it with get_kb_document first if you only mean to add to it.

Parameter	Type	Required	Default	Description
`document_id`	UUID	Yes	—	KB document UUID to update
`title`	string 1–255	—	—	New document title
`content_markdown`	string	—	—	Full replacement markdown body — not a patch or an append
`visibility`	`private` \| `public`	—	—	‘private’ = workspace-internal; ‘public’ = shareable outside the workspace
`parent_id`	UUID	—	—	Move to a different parent folder

`get_workspace_context`

Get Workspace Context · read-only Fetch the workspace’s AI context — a curated text blob from the knowledge base intended for agent priming. Use this at the start of a session to ground the agent in workspace-specific knowledge. Payload is capped server-side; for a full page use get_kb_document or search_kb_documents.

Parameter	Type	Required	Default	Description
`limit`	integer 1–50	—	`20`	Maximum number of context blocks to return (1-50, default 20)

Wiki

Read and edit the agent-maintained wiki — durable, section-addressable pages the workspace’s agents write to. Group id: wiki.

`wiki_search`

Search Agent Wiki · read-only Semantic search over the AGENT WIKI ONLY — knowledge that agents distilled and wrote back for reuse (decisions, procedures, research write-ups, customer intel). Search it FIRST, before CRM lookups, email scans or web research: one call can replace a whole research session. One of four separate retrieval stores: use search_entities for CRM records, search_kb_documents for human-authored Knowledge Base docs, and morphic_recall for cross-session memory about this user/workspace.

Parameter	Type	Required	Default	Description
`query`	string ≥ 1	Yes	—	What you want to know, in natural language
`max_results`	integer 1–50	—	`8`	Maximum wiki pages to return (1-50, default 8)
`hops`	integer 0–2	—	`1`	Multi-hop graph traversal over linked pages

`wiki_write`

Write Wiki Page · idempotent Create or replace a wiki page with DISTILLED knowledge (not transcripts). Write after completing research, making a decision, learning a procedure, or gathering customer intel — so no future session repeats the work. This is the Agent Wiki (agent-maintained, read-only for humans) — NOT the regular team Knowledge Base (use create_kb_document for that instead).

Parameter	Type	Required	Default	Description
`slug`	string ≥ 1	Yes	—	agent-wiki/<category>/<kebab-topic>
`title`	string ≥ 1	Yes	—	Human-readable page heading, e.g. ‘Q3 pricing decision’. The slug is the id; this is what people read.
`content_markdown`	string ≥ 1	Yes	—	Concise markdown. Link related pages with [[agent-wiki/…]].
`category`	`general` \| `research` \| `decisions` \| `procedures` \| `customer-intel` \| `summaries`	—	`"general"`	Top-level shelf this page belongs on; should match the <category> in the slug
`page_type`	`decision` \| `procedure` \| `research` \| `summary` \| `customer-intel` \| `meeting` \| `note`	—	—	What kind of page this is. Drives how it is surfaced later — pick the closest match rather than leaving it unset.
`confidence`	number 0–1	—	—	How sure you are of the content, 0-1. Use below 0.5 for inference from thin evidence so a reader knows to verify.
`source_refs`	string[]	—	—	e.g. crm:contact:123, email:456, url:https://…

`wiki_append`

Append to Wiki Page Add a new dated section to the END of an existing wiki page — the right tool for accumulating findings over time (running customer intel, follow-up notes). Nothing already on the page is touched, so prefer this over wiki_write when you are adding rather than restating; use wiki_edit_section to change an existing section, and wiki_write to author a page from scratch. Not idempotent: calling it twice appends twice.

Parameter	Type	Required	Default	Description
`slug`	string ≥ 1	Yes	—	Slug of the page to append to, e.g. agent-wiki/customer-intel/acme
`content_markdown`	string ≥ 1	Yes	—	Markdown body of the new section. Do not include the heading line itself.
`section_header`	string	—	—	Heading text for the appended section (without # marks); defaults to a dated header
`title`	string	—	—	Only used if the page doesn’t exist yet and needs to be created
`category`	`general` \| `research` \| `decisions` \| `procedures` \| `customer-intel` \| `summaries`	—	`"general"`	Only used if the page doesn’t exist yet and needs to be created

`wiki_edit_section`

Edit Wiki Section · idempotent Replace ONE named section of an existing wiki page, leaving every other section byte-identical. Prefer this over wiki_write when you only need to change or add a specific section (e.g. adding a subsection, correcting one part) — wiki_write replaces the whole page, which produces a confusing full-page diff for the human reviewing it if you don’t reproduce every other section verbatim. If no section with this exact heading exists yet, it’s appended as a new section.

Parameter	Type	Required	Default	Description
`slug`	string ≥ 1	Yes	—	Slug of the page to edit, e.g. agent-wiki/customer-intel/acme
`section_header`	string ≥ 1	Yes	—	Exact heading text of the section to replace (without the # marks)
`content_markdown`	string ≥ 1	Yes	—	New body for that section. Do not include the heading line itself.

`wiki_list`

List Wiki Pages · read-only Enumerate agent wiki pages (slug, title, category, last-updated) without reading any bodies — use it to see what the wiki already covers before writing a new page, or to find an exact slug for wiki_append / wiki_edit_section. It does NOT match on page content: to answer a question from the wiki, use wiki_search instead.

Parameter	Type	Required	Default	Description
`category`	`general` \| `research` \| `decisions` \| `procedures` \| `customer-intel` \| `summaries`	—	—	Only pages in this category; omit for all categories
`prefix`	string	—	—	Only pages whose slug starts with this, e.g. agent-wiki/research/
`limit`	integer 1–500	—	`100`	Maximum pages to return (1-500, default 100)

Memory

Semantic recall over the workspace’s stored knowledge and attachments, plus writing new memories back. Group id: memory.

`morphic_recall`

Recall Memory · read-only Search persistent CROSS-SESSION MEMORY ONLY — durable facts and preferences remembered about this user/workspace from past conversations. It does not see CRM records, KB docs or wiki pages. NOT a first resort: for any question about a workspace record of any object type, or about what has been happening, call ask_context first — it returns compacted briefs plus a semantic recall over the same indexed history, and tells you if it needs this tool. Reach here when ask_context comes back without what you need, or when the question is specifically about remembered preferences. One of four separate retrieval stores: use search_entities for CRM records of any object type, search_kb_documents for human-authored Knowledge Base docs, and wiki_search for agent-distilled team knowledge. Call with mode=“thinking” only when a prior fast recall was insufficient — it is slower and more expensive, never a first resort.

Parameter	Type	Required	Default	Description
`query`	string ≥ 1	Yes	—	What to recall
`mode`	`fast` \| `thinking`	—	`"fast"`	’fast’ = quick/cheap. ‘thinking’ = deeper, slower search over memory — use only if fast was insufficient.
`max_results`	integer 1–50	—	`8`	How many memories to return (1-50, default 8). Results land straight in context — raise it only when 8 proved too few.

`morphic_attachment_recall`

Recall Chat Attachments · read-only Semantically search documents/files the user previously uploaded in chat (PDFs, contracts, notes, etc.). Use when the user refers to an uploaded document without naming a specific attachment id. Do NOT use this for in-app chat turns that already list attachment ids — those are injected deterministically. Internally calls knowledge/recall with kinds=[“chat_attachment”].

Parameter	Type	Required	Default	Description
`query`	string ≥ 1	Yes	—	What to find in uploaded chat documents
`mode`	`fast` \| `thinking`	—	`"fast"`	’fast’ = quick/cheap. ‘thinking’ = deeper search.
`max_results`	integer 1–50	—	`8`	Maximum matching passages to return (1-50, default 8)

`morphic_remember`

Remember Store a durable fact or preference about THIS USER OR WORKSPACE in cross-session memory — things like how they want reports formatted, or a standing constraint that should survive into future conversations. Retrieved later by morphic_recall. Do NOT use it for CRM data (use create_entity / set_entity_field / create_note so it lands on the record) or for shared team knowledge (use wiki_write or create_kb_document instead).

Parameter	Type	Required	Default	Description
`content`	string ≥ 1	Yes	—	The fact to remember, written as a self-contained sentence with no chat context

Calendar

Read and manage calendar events on the user’s connected calendar, and check connection status. Group id: calendar.

`list_calendar_events`

List Calendar Events · read-only List SCHEDULED CALENDAR EVENTS — things on the calendar, past or upcoming, whether or not anyone recorded them. This is NOT list_meetings: that one returns Attendee-bot recordings with transcripts and recaps. Use this tool for “what’s on my calendar” / “my next meeting”; use list_meetings for “what was said in” / “the recap of” a past call. Filter by date range, linked CRM entity, or free-text search. For upcoming / this week / meetings coming up: ALWAYS pass start_date as now (ISO8601). Omitting both dates defaults the API to now→future — do not rely on paging the full history. For a named event (e.g. “Nat anniversary”), ALWAYS pass search with distinctive title words — do not page through the full calendar. Events synced from Google/Microsoft Calendar and events created here both show up.

Parameter	Type	Required	Default	Description
`start_date`	string	—	—	ISO8601 — only events ending on/after this. Required for upcoming lists — use current time.
`end_date`	string	—	—	ISO8601 — only events starting on/before this
`search`	string	—	—	REQUIRED for named lookups. Free-text match on title/description (case-insensitive). Example: search=“Nat anniversary”. Do not use query/q — only this field is honored.
`linked_entity_id`	UUID	—	—	Only events linked to this CRM entity
`linked_object_type_slug`	string	—	—	Narrows linked_entity_id lookup to this object type slug
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–100	—	`25`	Events per page (1-100, default 25)

`get_calendar_event`

Get Calendar Event · read-only Get one calendar event by its UUID — full description, times, location, attendees, and the Attendee meeting-bot status if one was requested for it. Use it after list_calendar_events when you need details the list view trims; it will not find an event by name, so search with list_calendar_events first if you only have a title.

Parameter	Type	Required	Default	Description
`event_id`	UUID	Yes	—	Calendar event UUID

`get_calendar_connection_status`

Get Calendar Connection Status · read-only Check whether Google Calendar and/or Microsoft Calendar are actually connected for this workspace/user. Call this BEFORE telling a user that calendar sync failed or that their calendar looks empty — an unconnected calendar is the usual cause and is a setup problem, not an error worth retrying. Parameters: none

`create_calendar_event`

Create Calendar Event Create a calendar event. Set join_with_meeting_bot to true to have the Attendee meeting bot join and record/transcribe this specific event (requires meeting_url). Creating a meeting cannot arm recording when the workspace recording default is off — the meeting is still created and the result includes a warning. To record anyway, use update_calendar_event with join_with_meeting_bot=true after the meeting exists. Attendee emails create/link CRM contacts unless create_records_from_attendees is false. Syncs to Google/Microsoft Calendar by default when connected.

Parameter	Type	Required	Default	Description
`title`	string 1–255	Yes	—	Event title as it appears on the calendar
`description`	string	—	—	Event body/agenda shown in the invite
`start_time`	string	Yes	—	ISO8601 datetime
`end_time`	string	Yes	—	ISO8601 datetime — must be after start_time
`color`	string	—	—	Hex color, e.g. ‘#3b82f6’
`location`	string	—	—	Physical location or room. For a video call use meeting_url instead
`meeting_url`	string ≤ 4096	—	—	Zoom/Meet/Teams URL — required for join_with_meeting_bot
`metadata`	object	—	—	Free-form key/value data stored on the event. Not shown to attendees
`attendees`	string[]	—	—	Attendee emails, e.g. [‘john@company.com’]
`create_records_from_attendees`	boolean	—	`true`	Create/link CRM contacts from attendee emails
`join_with_meeting_bot`	boolean	—	`false`	Request the Attendee meeting bot for this event
`sync_to_google`	boolean	—	`true`	Also create/update this event in the user’s connected Google Calendar. Default true; set false to keep it only in Morphic
`sync_to_microsoft`	boolean	—	`true`	Also create/update this event in the user’s connected Microsoft/Outlook calendar. Default true; set false to keep it only in Morphic

`update_calendar_event`

Update Calendar Event · idempotent Update fields on an existing calendar event. Only provided fields are changed. Set join_with_meeting_bot to true/false to request or cancel the Attendee meeting bot for this event.

Parameter	Type	Required	Default	Description
`event_id`	UUID	Yes	—	Calendar event UUID to update
`title`	string 1–255	—	—	New event title
`description`	string	—	—	New event body/agenda
`start_time`	string	—	—	ISO8601 datetime
`end_time`	string	—	—	ISO8601 datetime — must be after start_time
`color`	string	—	—	Hex color, e.g. ‘#3b82f6’
`location`	string	—	—	Physical location or room. For a video call use meeting_url instead
`meeting_url`	string ≤ 4096	—	—	Zoom/Meet/Teams URL — required for join_with_meeting_bot
`metadata`	object	—	—	Free-form key/value data stored on the event. Replaces the existing value
`join_with_meeting_bot`	boolean	—	—	Request or cancel the Attendee meeting bot for this event
`sync_to_google`	boolean	—	`true`	Also create/update this event in the user’s connected Google Calendar. Default true; set false to keep it only in Morphic
`sync_to_microsoft`	boolean	—	`true`	Also create/update this event in the user’s connected Microsoft/Outlook calendar. Default true; set false to keep it only in Morphic

`delete_calendar_event`

Delete Calendar Event · destructive · idempotent Delete a calendar event. This cannot be undone. Also removes it from Google/Microsoft Calendar if synced.

Parameter	Type	Required	Default	Description
`event_id`	UUID	Yes	—	Calendar event UUID to delete
`sync_to_google`	boolean	—	`true`	Also delete this event from the user’s connected Google Calendar. Default true; set false to remove it from Morphic only
`sync_to_microsoft`	boolean	—	`true`	Also delete this event from the user’s connected Microsoft/Outlook calendar. Default true; set false to remove it from Morphic only

Meetings

Meeting recordings and recaps: transcripts, follow-ups, record linking, and dispatching the note-taking bot. Group id: meetings.

`list_meetings`

List Meetings · read-only List ATTENDEE-BOT RECORDINGS — only past calls the meeting bot actually joined, transcribed and recapped. These are NOT calendar events: a meeting on the calendar that the bot never joined will not appear here, and nothing upcoming ever will. For “what’s on my calendar” or anything in the future, use list_calendar_events instead; use this when the user asks what was said, decided, or agreed in a past call.

Parameter	Type	Required	Default	Description
`linked`	`all` \| `linked` \| `unlinked`	—	`"all"`	’unlinked’ surfaces recordings not yet attached to any CRM record
`search`	string	—	—	Free-text search over title/summary
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–100	—	`25`	Recordings per page (1-100, default 25)

`get_meeting`

Get Meeting · read-only Get one Attendee-bot recording in full, including the ENTIRE transcript — a large payload that can dominate the context window for a long call. Only call it when you genuinely need verbatim wording; to check whether a topic came up, or to pull the few relevant lines, use search_meeting_transcripts instead, and prefer the recap preview from list_meetings for summaries.

Parameter	Type	Required	Default	Description
`meeting_id`	UUID	Yes	—	Meeting UUID

`get_meeting_follow_ups`

Get Meeting Follow-ups · read-only List the follow-up tasks already generated from a recorded meeting. These are REAL activity records that exist in the CRM — do not re-create them with create_activity; if the user asks for the action items from a call, read them here and reference them, and only use update_activity/complete_task to change their state.

Parameter	Type	Required	Default	Description
`meeting_id`	UUID	Yes	—	Meeting UUID
`limit`	integer 1–100	—	`25`	Maximum follow-ups to return (1-100, default 25)

`link_meeting_to_entity`

Link Meeting To Entity · idempotent Attach a meeting recap/transcript to a CRM record (a person, company or deal) so it shows up on that record’s timeline.

Parameter	Type	Required	Default	Description
`meeting_id`	UUID	Yes	—	Meeting UUID
`entity_id`	UUID	Yes	—	CRM entity UUID to link this meeting to
`object_type_slug`	string	—	—	Object type slug of the entity, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set.

`unlink_meeting_from_entity`

Unlink Meeting From Entity · idempotent Detach a meeting recap/transcript from whatever CRM record it is currently on, so it stops appearing on that record’s timeline. It takes no entity argument — it clears the single current link, so use it to correct a mis-link and then call link_meeting_to_entity with the right record. The recording itself is not deleted.

Parameter	Type	Required	Default	Description
`meeting_id`	UUID	Yes	—	Meeting UUID

`search_meeting_transcripts`

Search Meeting Transcripts · read-only Keyword search over meeting transcript text SCOPED TO ONE CRM RECORD — entity_type and entity_id are both required, so this is not a workspace-wide transcript search and cannot answer “did anyone ever mention X”. Resolve the record first with search_entities, then use this to check whether a topic came up and pull the matching lines, instead of loading a whole transcript with get_meeting.

Parameter	Type	Required	Default	Description
`q`	string ≥ 1	Yes	—	Plain keyword search query
`entity_type`	string	Yes	—	Record object type slug, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set.
`entity_id`	UUID	Yes	—	Record entity UUID
`limit`	integer 1–50	—	`20`	Maximum matching transcript excerpts to return (1-50, default 20)

`force_join_meeting_bot`

Force-Join Meeting Bot · open-world Immediately dispatch the Attendee meeting bot to join a scheduled calendar event’s call right now, rather than waiting for its normal scheduled join time. The event must have a meeting_url.

Parameter	Type	Required	Default	Description
`calendar_event_id`	UUID	Yes	—	Calendar event UUID whose call the bot should join now

Automations

Author, publish, run and inspect workflow automations, including their triggers and run history. Group id: automations.

`list_workflows`

List Workflows · read-only List CRM automations (workflows) with status and run stats. Call this first to see what automations already exist before creating a new one.

Parameter	Type	Required	Default	Description
`status`	`draft` \| `active` \| `paused`	—	—	Only automations in this lifecycle state; omit for all
`is_favorite`	boolean	—	—	Only automations the user starred
`search`	string	—	—	Keyword search across name/description
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–100	—	`25`	Automations per page (1-100, default 25)

`get_workflow`

Get Workflow · read-only Get one automation’s METADATA — name, status, trigger_summary, and run counters. It does NOT return the trigger/steps graph, so you cannot read or reason about an automation’s actual logic from this; pass the workflow_id to author_workflow to edit that logic, and use get_workflow_run to see what a specific execution actually did.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID

`list_workflow_triggers`

List Workflow Triggers · read-only List the trigger types available for automations (e.g. manual, scheduled, webhook, record_created, record_updated, activity_created), with the fields each one exposes as {{trigger.<field>}}. Call this before author_workflow if you need to know exactly which triggers/fields are valid.

Parameter	Type	Required	Default	Description
`limit`	integer 1–100	—	`50`	Maximum trigger types to return (1-100, default 50)

`create_workflow`

Create Workflow Create a new draft automation (metadata only — name/description). The automation has no trigger or steps yet; call author_workflow next to generate and save its actual logic from a natural-language description.

Parameter	Type	Required	Default	Description
`name`	string ≥ 1	Yes	—	Automation name
`description`	string	—	—	What this automation does, for teammates reading the list later.

`author_workflow`

Author Workflow Generate (or edit) an automation’s trigger + steps from a natural-language description, using the same AI Automation Builder the UI uses. Saves the result as a new draft version automatically — call publish_workflow afterward to make it live (it stays a draft otherwise). IMPORTANT: condition/branch nodes are NOT evaluated by the execution engine yet — describe linear automations only (trigger → step → step), not conditional logic. A failed step aborts the whole run, there’s no retry. If the assistant can’t build a valid graph from your description (e.g. a required choice is ambiguous), it replies with a clarifying question instead — workflow_config/version will be null in that case; answer the question and call this again with a more specific message. To iterate on an automation you already built with this tool, pass the current_config from the previous response’s version.workflow_config back in — otherwise each call starts a fresh graph. If you get HTTP 503 / ‘overloaded’ / rate limit, wait ~60s before retrying — do not hammer retries.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID to author/edit (create one first with create_workflow)
`message`	string ≥ 1	Yes	—	Natural-language description of the trigger and steps, e.g. “When a new company is created, create a follow-up task due in 2 days”
`current_config`	object	—	—	Pass back a previous response’s version.workflow_config to edit that graph instead of starting fresh

`publish_workflow`

Publish Workflow · idempotent Publish a saved automation version, making it the live one. If the workflow is still in ‘draft’ status, this also activates it. Get version_id from author_workflow’s response.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID
`version_id`	UUID	Yes	—	Version UUID to publish (from author_workflow’s response)

`update_workflow`

Update Workflow · idempotent Update an automation’s metadata — rename it, change its status (e.g. ‘paused’ to pause a running automation without deleting it), or mark it a favorite. Does not touch its trigger/steps — use author_workflow for that.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID
`name`	string	—	—	New automation name
`description`	string	—	—	New automation description
`status`	`draft` \| `active` \| `paused`	—	—	‘active’ = running, ‘paused’ = stops firing but is kept, ‘draft’ = never published
`is_favorite`	boolean	—	—	Star/unstar this automation
`retry_attempts`	integer ≥ 0	—	—	How many times a failed run is retried before giving up

`delete_workflow`

Delete Workflow · destructive · idempotent Soft-delete an automation. Prefer update_workflow with status=‘paused’ when you just want to stop it running.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID to delete

`enqueue_workflow_manual_run`

Run Workflow Now · open-world Manually run a saved automation version right now, outside its normal trigger. Executes for real (actions run against live CRM data) — this is not a dry run. version_id comes from author_workflow’s response.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID
`workflow_version_id`	UUID	Yes	—	Saved version UUID to execute

`list_workflow_runs`

List Workflow Runs · read-only List past runs of an automation — status, timing, and errors. Use to check whether an automation is actually firing and succeeding.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID
`page`	integer ≥ 1	—	`1`	1-based page number of results to return
`page_size`	integer 1–100	—	`25`	Runs per page (1-100, default 25), newest first

`get_workflow_run`

Get Workflow Run · read-only Get details of a single automation run — trigger payload, per-step outputs, and error message if it failed. Use to debug why an automation did (or didn’t) do something.

Parameter	Type	Required	Default	Description
`workflow_id`	UUID	Yes	—	Workflow UUID
`run_id`	UUID	Yes	—	Run UUID

Revenue Intelligence

Run the LLM-backed GTM analyses: pre/post-meeting packs, deal-risk scans, pipeline narration, executive digests and CRM hygiene. Group id: revenue-intelligence.

`run_crm_hygiene_scan`

Run CRM Hygiene Scan Scan the whole CRM for data-quality issues right now (missing required fields, deals without a next step, companies without contacts, contacts without a company) instead of waiting for the weekly scheduled scan. Workspace-wide — no entity argument needed. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose. Parameters: none

`run_pipeline_narration`

Run Pipeline Narration Generate a narrative summary of current deal pipeline movement right now, instead of waiting for the weekly scheduled digest. Workspace-wide — no entity argument needed. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose. Parameters: none

`run_executive_digest`

Run Executive Digest Generate the high-level executive digest (rolling up recent pipeline narration and workspace-visible deal risk flags) right now, instead of waiting for the weekly schedule. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose. Parameters: none

`run_deal_risk_scan`

Run Deal Risk Scan Assess risk on a specific deal right now (stale, no next step, negative sentiment, etc.), instead of waiting for the daily scheduled scan. Identify the deal by entity_id or name. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	—	—	Deal entity id to assess.
`deal_name`	string	—	—	Deal name, if entity_id is unknown.

`run_account_relationship_snapshot`

Run Account Relationship Snapshot Generate an account relationship snapshot for a company — relationship health, key contacts, recent meeting context. Runs on demand; identify the company by entity_id or name. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	—	—	Company entity id to snapshot.
`company_name`	string	—	—	Company name, if entity_id is unknown.

`run_prospecting_brief`

Run Prospecting Brief · open-world Generate a prospecting research brief for a company/prospect — web research synthesized into a summary, by existing CRM entity_id or a free-text research_query. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	—	—	CRM entity id to research (e.g. a company).
`research_query`	string	—	—	Free-text subject to research, if not an existing CRM entity.

`run_pre_meeting_brief`

Run Pre-Meeting Brief Load or generate prep notes (talking points, battle cards, entity context) for a specific upcoming meeting. Requires the meeting’s calendar_event_id — look it up with a calendar list/search tool first if you only have a meeting name or date. By default reuses an existing brief for that meeting; set force=true to regenerate. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`calendar_event_id`	UUID	Yes	—	The calendar event’s UUID, e.g. the `id` from list_calendar_events.
`force`	boolean	—	`false`	When false (default), return an existing pre_meeting_brief for this meeting if one exists. When true, always generate a new brief.

`run_post_meeting_pack`

Run Post-Meeting Pack Regenerate the meeting recap (summary, sentiment, action items) for a CRM record’s most recent recorded meeting, instead of waiting for the automatic recap. Always targets that entity’s LATEST meeting, not an arbitrary past one. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`entity_id`	UUID	Yes	—	CRM entity id (company/contact/deal) whose most recent meeting to recap.

`list_agent_feed_artifacts`

List Agent Feed Artifacts · read-only · idempotent List recent Agent Feed artifacts (Revenue Intelligence briefs already generated) — title, summary, and suggested-follow-up status for each. Use to answer questions about past briefs instead of regenerating one.

Parameter	Type	Required	Default	Description
`kind`	`post_meeting_pack` \| `pre_meeting_brief` \| `deal_risk_scan` \| `pipeline_narration` \| `executive_digest` \| `crm_hygiene_scan` \| `account_relationship_snapshot` \| `prospecting_brief`	—	—	Filter to one kind.
`limit`	integer 1–50	—	`10`	How many artifacts to return, newest first (1-50, default 10).

`get_agent_feed_artifact`

Get Agent Feed Artifact · read-only · idempotent Read the full content of one Agent Feed artifact by id — title, summary, full body, and every suggested follow-up with its id/label/status. Use before accepting, dismissing, or updating a specific suggested action. On web chat, after success call present with the returned title/summary/body_markdown (meeting prep → type meeting_prep; other kinds → type artifact_generic with kind) — do not only summarize in prose.

Parameter	Type	Required	Default	Description
`artifact_id`	UUID	Yes	—	The artifact’s UUID, from list_agent_feed_artifacts.

`accept_suggested_action`

Accept Suggested Action · open-world Accept and execute one suggested follow-up action from an Agent Feed artifact — the same as clicking Accept in the Agent Feed.

Parameter	Type	Required	Default	Description
`artifact_id`	UUID	Yes	—	The artifact’s UUID, from list_agent_feed_artifacts.
`action_id`	UUID	Yes	—	The suggested action’s UUID, from get_agent_feed_artifact.

`dismiss_suggested_action`

Dismiss Suggested Action · idempotent Dismiss (reject, without executing) one suggested follow-up action from an Agent Feed artifact.

Parameter	Type	Required	Default	Description
`artifact_id`	UUID	Yes	—	The artifact’s UUID, from list_agent_feed_artifacts.
`action_id`	UUID	Yes	—	The suggested action’s UUID, from get_agent_feed_artifact.

`update_suggested_action`

Update Suggested Action · idempotent Edit a suggested follow-up action’s label and/or args before it’s accepted — e.g. correct a drafted task’s title. Only works while the action is still pending.

Parameter	Type	Required	Default	Description
`artifact_id`	UUID	Yes	—	The artifact’s UUID, from list_agent_feed_artifacts.
`action_id`	UUID	Yes	—	The suggested action’s UUID, from get_agent_feed_artifact.
`label`	string	—	—	New human-readable label for this suggestion.
`args`	object	—	—	New args for the underlying tool call.

`get_revenue_intelligence_settings`

Get Revenue Intelligence Settings · read-only · idempotent Read the current Revenue Intelligence configuration for this workspace: which of the 8 kinds are enabled, their schedule, and delivery_channels (slack, telegram, or both) for proactive posts. Parameters: none

`update_revenue_intelligence_settings`

Update Revenue Intelligence Settings · idempotent Change Revenue Intelligence settings: enable/disable a kind, set its schedule, or change delivery_channels. Pass kind + patch to change one kind’s settings, and/or delivery_channels.

Parameter	Type	Required	Default	Description
`kind`	`post_meeting_pack` \| `pre_meeting_brief` \| `deal_risk_scan` \| `pipeline_narration` \| `executive_digest` \| `crm_hygiene_scan` \| `account_relationship_snapshot` \| `prospecting_brief`	—	—	Which Revenue Intelligence report to reconfigure. Required whenever `patch` is given — `patch` applies to this kind only. Omit to change delivery_channels alone.
`patch`	object	—	—	Partial settings for `kind` — only the fields you pass change; omitted fields keep their current values. Read them first with get_revenue_intelligence_settings.
`delivery_channels`	`slack` \| `telegram` \| `both`	—	—	Where proactive reports are posted. Workspace-wide, not per-kind, so it applies to every enabled kind at once.

`post_to_slack`

Post to Slack · open-world Post a message to this workspace’s connected Slack channel right now — use when the user explicitly asks you to send/deliver/post something to Slack, instead of just answering in chat.

Parameter	Type	Required	Default	Description
`message`	string	Yes	—	The message to post to Slack. Markdown-ish Slack mrkdwn is fine.
`title`	string	—	—	Optional bold header line shown above the message.

`post_to_telegram`

Post to Telegram · open-world Post a message to this workspace’s connected Telegram chat right now — use when the user explicitly asks you to send/deliver/post something to Telegram.

Parameter	Type	Required	Default	Description
`message`	string	Yes	—	The message to post to Telegram.
`title`	string	—	—	Optional header line shown above the message.

`publish_routine_report`

Publish Routine Report Call this when you finish a scheduled custom routine, to record what you found. Requires the routine_id given in your own instructions for this run — only call this while running a custom routine, never otherwise. Writes a brief to Briefs and marks this routine’s last run. Call it even when there is nothing noteworthy, with a body saying so.

Parameter	Type	Required	Default	Description
`routine_id`	string	Yes	—	This routine’s own id, exactly as given in your instructions.
`title`	string 1–200	Yes	—	Short title for this report.
`body_markdown`	string 1–20000	Yes	—	Markdown body summarizing what you found.
`summary`	string ≤ 500	—	—	One-sentence summary, if you have one.

External CRM sync

Push field changes on Morphic records out to a connected external CRM (e.g. HubSpot) and mirror the same change locally, and review records that changed on both sides at once. Group id: connectors.

`sync_linked_record`

Sync linked record to provider · open-world Create or update a record in a connected external system (HubSpot, Salesforce, Linear, Asana, …) and keep Morphic in sync. Pass record_ref (entity UUID for CRM, activity/task UUID for work). Optional domain=crm|work; optional toolkit when the record has exactly one provider link or a workspace CRM/tasks role is set. Linked records are updated; unlinked HubSpot/Salesforce contacts, companies/accounts, deals/opportunities, and Salesforce leads are created and linked when create is supported. Linear/Asana task create needs workspace provider defaults (team_id / workspace). Prefer list_workspace_connectors for connected toolkits, supports_create, and writeable field slugs. Unmapped keys appear in dropped_fields.

Parameter	Type	Required	Default	Description
`record_ref`	string	Yes	—	UUID of the Morphic entity (crm) or activity/task (work) to sync.
`domain`	`crm` \| `work`	—	—	crm = EAV entity (HubSpot/Salesforce). work = activity task (Linear/Asana).
`toolkit`	`hubspot` \| `salesforce` \| `linear` \| `asana` \| `apollo`	—	—	Which connected provider to write to. Omit when the record has exactly one link. apollo covers contact, deal, apollo_task and apollo_call — prefer log_apollo_call/ create_apollo_task for creating a new apollo_call/apollo_task (they push the required Apollo-only fields this generic tool does not collect).
`fields`	object	Yes	—	Field values to write, keyed by Morphic field slug — e.g. CRM {“phone_number”: “+1 555 0100”} or work {“subject”: “Ship dual-write”}. Unmapped keys are reported in dropped_fields.

`sync_entity_to_provider`

Sync record to connected CRM · open-world Compatibility alias for sync_linked_record (CRM entities). Create or update a record in a connected external CRM (HubSpot, Salesforce, Apollo, …) and keep Morphic in sync. Prefer sync_linked_record for Linear/Asana tasks. Linked entities are updated; unlinked HubSpot/Apollo contacts, HubSpot companies, and HubSpot/Apollo deals are created and the provider id is written back. toolkit is optional when the entity has exactly one provider link or a workspace CRM role is set. Prefer list_workspace_connectors for connected toolkits and writeable field slugs. Unmapped keys appear in dropped_fields.

Parameter	Type	Required	Default	Description
`entity_id`	string	Yes	—	UUID of the Morphic entity to sync.
`toolkit`	`hubspot` \| `salesforce` \| `apollo`	—	—	Which connected provider to write to. Omit when the entity has exactly one link. apollo covers contact and deal.
`fields`	object	Yes	—	Field values to write, keyed by Morphic field slug — e.g. {“phone_number”: “+1 555 0100”, “name”: “Vraj Shah”, “city”: “Boston”}. Unmapped keys are reported in dropped_fields.

`list_workspace_connectors`

List workspace connectors · read-only List external connectors for this workspace (catalog ∩ ACTIVE Composio connections — HubSpot, Salesforce, Linear, Asana, …) plus workspace connector_roles (crm / tasks / meetings). Use to see which CRM, task, and meeting-recorder tool the agent should pair with Morphic, and which field slugs sync via sync_linked_record / sync_entity_to_provider. Parameters: none

`list_record_mismatches`

List mismatched records · read-only List CRM records that changed in BOTH Morphic and the connected external CRM (HubSpot / Salesforce) since the last sync, so neither side can be applied without discarding an edit. Returns the conflicting fields side by side (morphic vs provider value) with when each side changed. Use this to ask the user to review a mismatched record, then call resolve_record_mismatch with their choice.

Parameter	Type	Required	Default	Description
`limit`	integer 1–100	—	—	Max mismatches to return (default 20). Oldest first.

`resolve_record_mismatch`

Resolve mismatched record · open-world Settle a record from list_record_mismatches once the user has chosen a version. take_provider copies the external CRM’s values into Morphic; keep_morphic pushes Morphic’s values out to the external CRM so it stops disagreeing; dismiss clears the flag without changing either side (the external CRM will win on a later sync). Show the user both versions and let them choose before calling this.

Parameter	Type	Required	Default	Description
`toolkit`	`hubspot` \| `salesforce`	Yes	—	Provider the record is mismatched against.
`object_key`	string	Yes	—	contact \| company \| deal \| account \| opportunity \| lead.
`provider_id`	string	Yes	—	External record id, as returned by list_record_mismatches.
`resolution`	`keep_morphic` \| `take_provider` \| `dismiss`	Yes	—	The user’s choice.

`search_external_records`

Search HubSpot / Linear / Salesforce / Asana · read-only · open-world Search a connected external system by name, email, or domain when there is no Morphic record and no provider id. Use this to find HubSpot company XYZ, a Salesforce account, a Linear issue, or a contact/deal already in this workspace’s own Apollo account. Returns provider_record_id to pass to sync_linked_record (toolkit + object_key). For NET-NEW Apollo prospects not yet in this CRM, use search_apollo_prospects instead — this only searches records that already exist on the connected side. Omit toolkit to search the workspace CRM and tasks providers.

Parameter	Type	Required	Default	Description
`query`	string	Yes	—	Name, email, domain, or issue title (e.g. XYZ).
`toolkit`	`hubspot` \| `salesforce` \| `linear` \| `asana` \| `apollo`	—	—	Optional. Defaults to workspace CRM + tasks roles.
`object_key`	string	—	—	Optional. contact, company, deal, account, opportunity, lead, or task.
`limit`	number	—	—	Max hits (default 8).

`discover_composio_tools`

Discover connected integration tools · read-only · open-world Discover read-only tools for one integration explicitly selected by the user. Use the toolkit slug from the selected integration context. Without tool_name, returns a COMPACT browse list (name + one-line description only, no schema) — pick the tool you need from that list, then call this again WITH tool_name to get that one tool’s full description and input_schema before calling call_composio_read_tool. Do not skip the tool_name call: the browse list deliberately omits input_schema so it stays small.

Parameter	Type	Required	Default	Description
`toolkit`	string ≥ 1	Yes	—	Selected Composio toolkit slug.
`tool_name`	string 1–200	—	—	Optional exact tool name from a prior call with no tool_name. Returns that one tool’s full description + input_schema instead of the browse list.

`call_composio_read_tool`

Call a connected read-only integration tool · read-only · open-world Call one read-only tool returned by discover_composio_tools. The backend revalidates the selected toolkit, connection ownership, and tool allowlist before execution.

Parameter	Type	Required	Default	Description
`toolkit`	string ≥ 1	Yes	—	Selected Composio toolkit slug.
`tool_name`	string ≥ 1	Yes	—	Exact discovered tool name.
`arguments`	object	—	`{}`	Arguments matching the discovered tool schema.

Amplemarket

Use the asking user’s own Amplemarket seat — check their connection, discover which of the 9 tool categories their plan includes, and run one. Per person, not per workspace. Group id: amplemarket.

`get_amplemarket_connection_status`

Check your Amplemarket connection · read-only Check whether the person asking has connected their OWN Amplemarket account, and how many teammates have connected theirs. Amplemarket is a named-seat product connected per person, so there is no workspace-wide connection: a teammate being connected does NOT let this user act. Use this before suggesting any Amplemarket action, and to answer ‘why can’t I use Amplemarket?’ accurately. Amplemarket is for LIVE ENGAGEMENT on things already in motion (a reply, a sequence, deliverability) — for finding or enriching a company/person, prefer Apollo instead. Parameters: none

`list_amplemarket_capabilities`

List your Amplemarket capabilities · read-only · open-world List what THIS user’s Amplemarket account can actually do right now: which of the 9 categories (Searcher, Enrichment, Contacts & Accounts, Lead Lists, Sequences, Workflows, Analytics, Duo, Unibox & Tasks) are available to them, and the exact tool names and argument schemas inside each. ALWAYS call this before call_amplemarket_tool — Amplemarket tool names are not a fixed list and differ per person by plan tier and seat. Categories reported as unavailable are not in that user’s plan: do not offer them. Scope check before you call this: Amplemarket is for LIVE ENGAGEMENT on something already in motion (a reply, a sequence, deliverability, an inbox task) — if the ask is to FIND or ENRICH a company or person, prefer Apollo instead.

Parameter	Type	Required	Default	Description
`refresh`	boolean	—	—	Re-read the live tool list instead of the cached one. Use after the user changes their Amplemarket plan or reconnects.

`call_amplemarket_tool`

Run an Amplemarket tool · open-world Run one Amplemarket tool using this user’s own connected seat. Get tool_name and its arguments from list_amplemarket_capabilities first — never guess a name. This spends the USER’S OWN Amplemarket credits (enrichment is about 0.5 credits per record) and can write into their sequences, lead lists and tasks, so confirm with them before running anything that touches more than a handful of records. Use this for LIVE ENGAGEMENT work only — replies, sequences, deliverability, inbox tasks. Discovery and enrichment belong to Apollo, which is workspace-wide and consistent for every teammate. An Amplemarket record and an Apollo record for the same person share no identifier: never assume they refer to each other.

Parameter	Type	Required	Default	Description
`tool_name`	string 1–200	Yes	—	Exact tool name from list_amplemarket_capabilities, copied verbatim.
`arguments`	object	—	—	Arguments for that tool, matching the input schema list_amplemarket_capabilities reported for it.

TinyFish

Search the web, read pages, and drive a real browser to complete website tasks, using the asking user’s own TinyFish account. Search and page reads are free; browser automation is metered against that user’s wallet. Per person, not per workspace. Group id: tinyfish.

`get_tinyfish_connection_status`

Check your TinyFish connection · read-only Check whether the person asking has connected their OWN TinyFish account, and how many teammates have connected theirs. TinyFish is connected per person and metered against that person’s own wallet, so there is no workspace-wide connection: a teammate being connected does NOT let this user act. Use this before suggesting any TinyFish action, and to answer ‘why can’t I use TinyFish?’ accurately. Parameters: none

`tinyfish_search`

Search the web · read-only · open-world Search the web for current, source-backed facts using this user’s TinyFish account. FREE — use it first for anything current, public or external: today’s/latest questions, weather, documentation and API setup, product/company/tool explanations, comparisons, and ‘what is’ / ‘how does it work’ questions about real technologies, standards or companies. Use it even when the user doesn’t say ‘search’. Cheaper in tokens than fetching pages, so use it before tinyfish_fetch_content whenever the right page isn’t known yet. Skip it only when the answer should come purely from workspace data, or the user said not to use external sources.

Parameter	Type	Required	Default	Description
`query`	string 1–2000	Yes	—	What to search for.
`location`	string	—	—	Geo-target the search, e.g. ‘United Kingdom’.
`domain_type`	`web` \| `news` \| `research_paper`	—	—	Scope of the search. Defaults to ‘web’.
`recency_minutes`	integer ≥ 0	—	—	Only results from the past N minutes. Do NOT combine with after_date/before_date.
`after_date`	string	—	—	YYYY-MM-DD lower bound.
`before_date`	string	—	—	YYYY-MM-DD upper bound.
`include_domains`	string	—	—	Comma-separated domains to restrict results to.
`exclude_domains`	string	—	—	Comma-separated domains to remove from results.
`purpose`	string	—	—	Short statement of why you are searching, so results can be ranked against the underlying intent. Optional.

`tinyfish_fetch_content`

Read web pages · read-only · open-world Read one or more web pages and extract clean, structured content, using this user’s TinyFish account. FREE. Use when the user gives a URL, or after tinyfish_search when a grounded answer needs detail from a specific source: summarising pages, extracting article/docs/product/pricing content, inspecting documentation. Renders in a real browser, so JavaScript-heavy pages work, and is preferred over raw HTTP fetching. Up to 10 URLs per call, fetched in parallel. This tool only READS — use tinyfish_run_web_automation when the task needs clicking, navigating, form-filling or login.

Parameter	Type	Required	Default	Description
`urls`	string[]	Yes	—	Up to 10 URLs, fetched in parallel.
`format`	`markdown` \| `html` \| `json`	—	—	Output format. Defaults to markdown.
`links`	boolean	—	—	Also return outbound links found on the page.
`image_links`	boolean	—	—	Also return image URLs found on the page.
`include_selectors`	string[]	—	—	CSS selectors to extract only, e.g. [‘article’] or [‘main’, ‘#content’].
`exclude_selectors`	string[]	—	—	CSS selectors to strip before extraction, e.g. [‘.comments’].
`ttl`	integer ≥ 0	—	—	Cache freshness tolerance in seconds.
`per_url_timeout_ms`	integer ≥ 0	—	—	Per-URL wall-clock timeout budget.
`purpose`	string	—	—	Short statement of why you are fetching these URLs, so extraction can be tailored to the intent. Optional.

`tinyfish_run_web_automation`

Run a web automation · open-world Drive a real browser to complete ONE user-directed website task on this user’s TinyFish account: navigating a page, clicking, filling forms, logging in, or completing a workflow. This is METERED against the USER’S OWN TinyFish wallet — confirm with them before running it. Use it only when the task genuinely needs interaction: to find information use tinyfish_search, and to read a page use tinyfish_fetch_content — both are free. Runs take a few minutes and return a run_id: poll it with tinyfish_get_run rather than starting the run again.

Parameter	Type	Required	Default	Description
`task`	string 1–4000	Yes	—	What to do on the site, in plain language — the navigation, clicks, form entries or workflow to complete.
`url`	string	—	—	Page to start from.
`purpose`	string	—	—	Why this is being run. Optional.

`tinyfish_get_run`

Check a web automation run · read-only · open-world Check the status and result of a web automation started with tinyfish_run_web_automation. FREE — it only reads state, and is the correct way to wait: while the status is pending or running, call this again with the same run_id rather than starting a new run. When it reports completed, failed or cancelled, the result or error is included — present that to the user. Omit run_id to list recent runs if the id was lost.

Parameter	Type	Required	Default	Description
`run_id`	string	—	—	Run to check, from tinyfish_run_web_automation. Omit to list recent runs.

`list_tinyfish_capabilities`

List your TinyFish tools · read-only · open-world List the exact TinyFish tools THIS user’s account exposes right now. ALWAYS call this before call_tinyfish_tool — TinyFish tool names are not a fixed list and differ per account and client, so they are never guessable. For web search, page reading, browser automation or run polling, prefer the dedicated tinyfish_* tools instead; this is for everything else (batching, browser sessions, usage and wallet reads). Tools already covered by a dedicated tool are marked with prefer_instead. Parameters: none

`call_tinyfish_tool`

Run a TinyFish tool · open-world Run one TinyFish tool using this user’s own connected account. Get tool_name from list_tinyfish_capabilities first — never guess a name. Use this ONLY for capabilities the dedicated tools don’t cover (batching, browser sessions, usage and wallet reads): for web search use tinyfish_search, for reading pages use tinyfish_fetch_content, for browser interaction use tinyfish_run_web_automation. Automation and big-search tools reached this way spend the USER’S OWN TinyFish wallet, so confirm with them before running anything bulk.

Parameter	Type	Required	Default	Description
`tool_name`	string 1–200	Yes	—	Exact tool name from list_tinyfish_capabilities, copied verbatim.
`arguments`	object	—	—	Arguments for that tool, matching the input schema TinyFish reported for it.

Meeting notetakers

Search and read the asking user’s meeting transcripts, summaries and action items across every notetaker they have connected (Granola, Fireflies, Fathom, Otter, Circleback, Read.ai, Sybill, Plaud, tl;dv, Gong). Read-only, and per person rather than per workspace — a connected teammate does not let this user read anything. Group id: notetakers.

`list_notetaker_connections`

Check your meeting notetaker connections · read-only List which meeting notetakers the person asking has connected (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong). Notetakers are connected per person and read that person’s own meetings, so there is no workspace-wide connection: a teammate being connected does NOT let this user read anything. Call this before telling someone you cannot find their meetings — the honest answer differs depending on whether they have connected anything at all. Parameters: none

`search_notetaker_meetings`

Search meeting transcripts · read-only Search this person’s meeting transcripts and notes across EVERY notetaker they have connected. Use for anything about what was said, decided or promised in a meeting. Pass the user’s question verbatim — do not pre-extract names or dates. Leave vendor unset unless they named one; searching all their connections is almost always what they want. Note this searches the VENDOR’s copy directly — for meetings already ingested into Morphic, ask_context is usually better because it also covers email, Slack and CRM records.

Parameter	Type	Required	Default	Description
`query`	string	Yes	—	The user’s question, verbatim.
`vendor`	string	—	—	Restrict to one notetaker (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong). Omit to search all.
`limit`	integer 1–50	—	—	Maximum meetings to return (1-50). Defaults to the vendor’s own page size.

`list_recent_notetaker_meetings`

List recent meetings · read-only List this person’s recent meetings from their connected notetakers. Use when they ask WHICH meetings they had; for what was SAID in one, use search_notetaker_meetings or get_notetaker_meeting instead.

Parameter	Type	Required	Default	Description
`vendor`	string	—	—	Restrict to one notetaker (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong).
`limit`	integer 1–50	—	—	Maximum meetings to return (1-50). Defaults to the vendor’s own page size.
`since`	string	—	—	ISO-8601 date or datetime. Omit for the vendor’s default window.

`get_notetaker_meeting`

Get one meeting in full · read-only Fetch one meeting’s full detail — transcript, summary, attendees — from a specific notetaker. Both arguments come from a previous search_notetaker_meetings or list_recent_notetaker_meetings result: meeting ids are the vendor’s own and are NOT interchangeable between vendors.

Parameter	Type	Required	Default	Description
`vendor`	string	Yes	—	Which notetaker the id belongs to (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong).
`meeting_id`	string	Yes	—	The vendor’s own meeting or recording id.

`get_notetaker_action_items`

Get a meeting’s action items · read-only Fetch the action items a notetaker extracted for one meeting. Prefer this over re-deriving them from a transcript: the vendor has already done it, and its list is what the user sees in that product. Some vendors fold action items into the summary instead — this says so rather than failing.

Parameter	Type	Required	Default	Description
`vendor`	string	Yes	—	Which notetaker the id belongs to (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong).
`meeting_id`	string	Yes	—	The vendor’s own meeting or recording id.

`list_notetaker_tools`

List a notetaker’s own tools · read-only List the tool names one connected notetaker actually exposes to this user. Vendor surfaces differ by plan and change without notice, so read this before using call_notetaker_tool rather than guessing a name.

Parameter	Type	Required	Default	Description
`vendor`	string	Yes	—	Which connected notetaker to introspect (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong).

`call_notetaker_tool`

Call a notetaker tool directly · open-world Escape hatch: call any tool a connected notetaker exposes, by its own name. Use ONLY when the neutral tools (search_notetaker_meetings, list_recent_notetaker_meetings, get_notetaker_meeting, get_notetaker_action_items) do not cover what is needed. Call list_notetaker_tools first — passing a name the user’s account does not expose will simply fail.

Parameter	Type	Required	Default	Description
`vendor`	string	Yes	—	Which connected notetaker to call (granola, fireflies, fathom, otter, circleback, read_ai, sybill, plaud, tldv, gong).
`tool`	string	Yes	—	The vendor’s own MCP tool name.
`arguments`	object	—	—	Arguments for the vendor tool, shaped exactly as that tool defines them. list_notetaker_tools returns each tool’s schema — read it rather than guessing key names.

Apollo

Search Apollo’s global prospect database, enrich people and companies, log calls and tasks that push into Apollo, and enroll contacts in an existing Apollo sequence. Workspace-wide, connected once via Composio. Group id: apollo.

`search_apollo_prospects`

Search Apollo’s global prospect database · read-only · open-world Search Apollo’s global prospect database for people matching filters (job title, location, company headcount). Use this to find NET-NEW prospects — people who may not exist in this CRM or in this workspace’s own Apollo account yet. For contacts already in this workspace’s Apollo account, use search_external_records with toolkit=‘apollo’ instead. Spends real Apollo credits per call — confirm scope with the user before running a broad or repeated search. Combining many strict filters can return zero results; start broad and narrow iteratively. Null email/phone fields on returned people are normal, not errors — enrich_apollo_person can sometimes fill them in, at additional credit cost.

Parameter	Type	Required	Default	Description
`person_titles`	string[]	—	—	Job titles to match, e.g. [‘VP of Sales’, ‘Head of Sales’].
`person_locations`	string[]	—	—	Locations, e.g. [‘United States’].
`organization_num_employees_ranges`	string[]	—	—	Company headcount ranges, e.g. [‘50,200’] (Apollo’s range format).
`q_keywords`	string	—	—	Free-text keyword filter.
`page`	integer ≥ 1	—	—	Default 1.
`per_page`	integer 1–100	—	—	Default 10.

`enrich_apollo_person`

Enrich a person via Apollo · read-only · open-world Enrich one person’s profile via Apollo — full name, title, company, location, and (when available) email/phone. Requires email, linkedin_url, or first_name+last_name plus organization_name/domain — name-only usually returns no match. Spends real Apollo credits per call, and a miss (no match found) is a normal, valid outcome, not an error. Does not reveal phone numbers — that costs extra credits and isn’t wired up yet.

Parameter	Type	Required	Default	Description
`email`	string	—	—	Work email. The strongest single identifier — use it alone when you have it.
`linkedin_url`	string	—	—	LinkedIn profile URL. Next strongest identifier after email.
`first_name`	string	—	—	Given name. Only useful with last_name AND organization_name or domain.
`last_name`	string	—	—	Family name. Only useful with first_name AND organization_name or domain.
`organization_name`	string	—	—	Employer name, e.g. ‘Apollo’. Use domain instead when you know it — it matches far more reliably.
`domain`	string	—	—	Company domain, e.g. ‘apollo.io’.

`enrich_apollo_organization`

Enrich a company via Apollo · read-only · open-world Enrich a company’s profile via Apollo by domain — funding, headcount, tech stack, industry, and more. Results are most meaningful when the company already exists in Apollo’s database. Spends real Apollo credits per call and may be unavailable on free plans; a miss (no match) is a normal, valid outcome, not an error.

Parameter	Type	Required	Default	Description
`domain`	string ≥ 1	Yes	—	Company base domain, e.g. ‘apollo.io’ (not ‘www.apollo.io’).

`search_apollo_sequences`

Search this workspace’s Apollo sequences · read-only Search this workspace’s own Apollo outreach sequences by name. Use this before add_apollo_contacts_to_sequence — you need a real sequence_id and emailer_campaign_id (they are the same value) from here, never guessed. Apollo has no tool to create or activate a sequence — this only finds sequences a human already built and turned on in Apollo’s own UI. Read-only, no Apollo credits spent.

Parameter	Type	Required	Default	Description
`q_name`	string	—	—	Name or part of the name of the sequence to search for.
`page`	integer ≥ 1	—	—	Default 1.
`per_page`	integer 1–100	—	—	Default 25.

`list_apollo_email_accounts`

List this workspace’s connected Apollo email accounts · read-only List the email accounts connected to this workspace’s Apollo account. Use this before add_apollo_contacts_to_sequence — its send_email_from_email_account_id argument must be a real id from here, never guessed. Read-only, no Apollo credits spent, no arguments. Parameters: none

`add_apollo_contacts_to_sequence`

Add contacts to an Apollo sequence · open-world Enroll one or more existing Apollo contacts into an existing, already-active Apollo sequence. This is the only real outreach action Apollo/Composio expose — there is no tool to send a one-off email or to create/activate a sequence, only to add contacts to one a human already built. Triggers real outbound emails to real people once the sequence runs its next step — call search_apollo_sequences and list_apollo_email_accounts first to get real ids, and confirm with the user before running this. Never guess sequence_id, emailer_campaign_id, or send_email_from_email_account_id.

Parameter	Type	Required	Default	Description
`contact_ids`	string[]	Yes	—	Apollo contact ids to enroll — from search_external_records (toolkit=‘apollo’) or a prior create/enrich, never invented.
`sequence_id`	string	Yes	—	From search_apollo_sequences — the sequence to enroll contacts into.
`emailer_campaign_id`	string	Yes	—	From search_apollo_sequences — should match sequence_id.
`send_email_from_email_account_id`	string	Yes	—	From list_apollo_email_accounts — which connected inbox sends the emails.
`sequence_no_email`	boolean	—	—	If true, also add contacts with no email address. Default false.

`update_apollo_contact_sequence_status`

Update a contact’s status in an Apollo sequence · open-world Change an Apollo contact’s status within a sequence they are already enrolled in — pause them, mark them replied/finished, bounced, or unsubscribed. Cannot set status to ‘active’: Apollo’s own API rejects that on this action — use add_apollo_contacts_to_sequence to (re)activate someone instead. Real, externally-visible effect on live outreach (e.g. ‘unsubscribed’ stops all future emails to this contact in this sequence) — confirm with the user before running this.

Parameter	Type	Required	Default	Description
`status`	`paused` \| `finished_replied` \| `finished_not_replied` \| `bounced` \| `unsubscribed`	Yes	—	New status. ‘active’ is not supported here.
`contact_id`	string	Yes	—	Apollo contact id.
`sequence_id`	string	Yes	—	From search_apollo_sequences.

`log_apollo_call`

Log a call and push it to Apollo · open-world Log a phone call and push it to Apollo as a call record, when the linked contact is Apollo-linked. Use this instead of log_call when the call should show up in Apollo, not just the CRM. contact_id, when given, must already be Apollo-linked for the push to happen — the call is still logged in Morphic either way, and the response says whether the Apollo push actually happened.

Parameter	Type	Required	Default	Description
`subject`	string	Yes	—	Subject/title for the call log.
`description`	string	—	—	Call notes or summary — becomes Apollo’s note.
`duration_minutes`	integer	—	—	Duration of the call in minutes.
`contact_id`	string	—	—	Morphic contact UUID, ideally already Apollo-linked.
`status`	`queued` \| `ringing` \| `in-progress` \| `completed` \| `no_answer` \| `failed` \| `busy`	—	—	Apollo call status. Default ‘completed’.

`create_apollo_task`

Create a task and push it to Apollo · open-world Create a task and push it to Apollo as an Apollo task. Requires an already Apollo-linked contact_id and an apollo_owner (an Apollo team member — name, email, or Apollo user id, resolved against this workspace’s Apollo user directory) — Apollo’s own API requires both, this is not an artificial restriction, and the call fails closed (no Morphic task is created either) if the contact isn’t Apollo-linked. Use create_task instead for an ordinary CRM-only task. apollo_owner is distinct from an optional ‘assignee’ (a Morphic workspace member) — do not conflate the two.

Parameter	Type	Required	Default	Description
`title`	string	Yes	—	Task title — becomes Apollo’s note context.
`note`	string	—	—	Task description / note.
`contact_id`	string	Yes	—	Morphic contact UUID. Must already be Apollo-linked.
`apollo_owner`	string	Yes	—	Apollo team member who owns this task — name, email, or Apollo user id.
`due_date`	string	Yes	—	ISO 8601 due date/time, e.g. ‘2026-09-15T10:00:00Z’.
`task_type`	`call` \| `outreach_manual_email` \| `linkedin_step_connect` \| `linkedin_step_message` \| `linkedin_step_view_profile` \| `linkedin_step_interact_post` \| `action_item`	—	—	Default ‘action_item’.
`status`	`scheduled` \| `completed` \| `skipped`	—	—	Default ‘scheduled’.
`priority`	`high` \| `medium` \| `low`	—	—	Task priority in Apollo. Defaults to medium when omitted.
`assignee`	string	—	—	Morphic workspace-member UUID to assign the CRM-side task to. Distinct from apollo_owner — see tool description.

Clay

Search Clay’s GTM database, run Clay routines and check their results, read Clay Tables data, and check the workspace’s Clay credit balance. Workspace-wide, one API key for the whole team — connected directly to Clay’s Developer API, not via Composio. Group id: clay.

`get_clay_connection_status`

Check this workspace’s Clay connection · read-only Check whether THIS WORKSPACE has connected a Clay API key. Clay is workspace-scoped — unlike Amplemarket, every teammate shares the same connection, so there is no per-person answer here. Use this before suggesting any Clay action. Parameters: none

`check_clay_credits`

Check this workspace’s Clay credit balance · read-only · open-world Read this workspace’s Clay Data Credits / Actions balance. Call this before a bulk search_clay or run_clay_routine call to confirm there’s enough balance for it. Parameters: none

`get_clay_search_reference`

Get Clay’s search-query authoring reference · read-only · open-world Fetch Clay’s own reference for writing a Clay search query. search_clay takes Clay’s SQL-like DSL (SELECT FROM PEOPLE | COMPANIES | JOBS), not prose — call this first to translate a user’s description of an audience into that syntax. Costs no credits. Parameters: none

`list_clay_routines`

List registered Clay routines · read-only List the Clay routines registered for this workspace, by name. Call this before run_clay_routine — routines are referenced by name, and Clay has no API to discover them, so only routines an admin has registered can be run. Costs no credits. Parameters: none

`search_clay`

Search Clay’s GTM database · read-only · open-world Search Clay’s GTM database for people or companies matching a natural-language query. Spends this workspace’s Clay credits — call check_clay_credits first before a large search. Clay and Apollo both do discovery/enrichment and can overlap significantly; ask the user which they mean if both are connected and it isn’t obvious.

Parameter	Type	Required	Default	Description
`query`	string 1–2000	Yes	—	Natural-language description of who or what to find, e.g. ‘VP of Sales at Series B fintech companies in the US’.
`source_type`	`people` \| `companies`	—	—	Leave unset to let Clay infer it from the query.
`limit`	integer 1–1000	—	—	Default 25.

`run_clay_routine`

Run a Clay routine · open-world Run a Clay routine — a custom enrichment/workflow built in the Clay UI — against 1-100 items, by its registered NAME (call list_clay_routines first). Spends this workspace’s Clay credits and can write into the routine’s own downstream destinations (lead lists, sequences). Routines run asynchronously: use get_clay_routine_run with the returned run id to check progress and results rather than assuming this call finishes the work.

Parameter	Type	Required	Default	Description
`routine`	string 1–200	Yes	—	The NAME of a registered Clay routine, as returned by list_clay_routines (e.g. ‘Find work email’). End users are not expected to know Clay’s opaque `function:t_…` ids; a raw id is accepted only as a fallback.
`items`	object[]	Yes	—	1-100 items to run the routine against.

`get_clay_routine_run`

Check a Clay routine run’s progress · read-only · open-world Check progress and results for a routine run started with run_clay_routine. Read-only — does not spend additional credits or re-trigger the routine.

Parameter	Type	Required	Default	Description
`routine_run_id`	string 1–200	Yes	—	The run id returned by run_clay_routine.

`run_clay_table_query`

Query a Clay table · read-only · open-world Query data already sitting in a Clay table. Requires an Enterprise Clay plan — if this workspace’s Clay account isn’t on that tier, this returns an honest ‘not available on your plan’ result rather than failing silently.

Parameter	Type	Required	Default	Description
`query`	string 1–2000	Yes	—	Structured query to run against Clay Tables.

Clay (MCP)

Prospect and enrich companies and contacts via Clay’s own hosted MCP server, using the asking user’s own OAuth connection. Per person, not per workspace — unlike the Clay group above, which is one shared workspace API key. Group id: clay_mcp.

`get_clay_mcp_connection_status`

Check your own Clay MCP connection · read-only Check whether the ASKING USER has connected their OWN Clay account via OAuth. Clay MCP is per-person — a connected teammate does NOT let this user act. Use this before suggesting any Clay MCP action. Parameters: none

`check_clay_mcp_credits`

Check this user’s Clay credit balance · read-only · open-world Check whether this Clay workspace has credits available (workspace, sales-rep, and budget credits where enabled). Call this before find_clay_mcp_company or find_clay_mcp_contacts_at_company, which spend credits. Parameters: none

`get_clay_mcp_workspace`

Check which Clay workspace this user is connected to · read-only · open-world Report which Clay workspace this user’s connection is pinned to (name, id, URL). Use when the user asks which Clay workspace they are connected to. Parameters: none

`find_clay_mcp_company`

Prospect a company via Clay · read-only · open-world Prospect and research a single company’s PUBLICLY AVAILABLE info by domain or LinkedIn URL (e.g. ‘Tell me about Stripe’, “What’s OpenAI’s funding?”). NOT for the user’s own CRM accounts/deals. Never add company_data_points unless the user explicitly asked for that data — enrichments cost credits. Returns a task_id — follow up with get_clay_mcp_task_context to read enrichment results. There is NO tool here to run a saved Clay routine, Workflow, or Claygent by name — if asked to run one, say so plainly rather than stuffing its name into a ‘Custom’ data point as a substitute.

Parameter	Type	Required	Default	Description
`company_identifier`	string ≥ 1	Yes	—	Domain (e.g. ‘stripe.com’) or LinkedIn company URL. Company names alone will fail — convert a known name to its domain first.
`company_data_points`	object[]	—	—	Only include a data point the user explicitly asked for.

`find_clay_mcp_contacts_at_company`

Find contacts at a company via Clay · read-only · open-world Find TYPES of people at a company by role/title/department (e.g. ‘engineers at Stripe’, ‘VPs at OpenAI’). For SPECIFIC named people, this is the wrong tool. Filters combine with AND; values within one filter combine with OR. Never filter results yourself — re-call this tool with adjusted filters. Never add data points unless the user explicitly asked for them — enrichments cost credits. Returns a task_id — follow up with get_clay_mcp_task_context to read results. There is NO tool here to run a saved Clay routine, Workflow, or Claygent by name — if asked to run one, say so plainly rather than stuffing its name into a ‘Custom’ data point as a substitute.

Parameter	Type	Required	Default	Description
`company_identifier`	string ≥ 1	Yes	—	Domain (e.g. ‘stripe.com’) or LinkedIn company URL.
`contact_filters`	object	—	—	Who to look for at the company. Filters combine with AND; values inside one filter combine with OR. Omit to get a general sample of contacts.
`contact_data_points`	object[]	—	—	Only include a data point the user explicitly asked for.
`company_data_points`	any[]	—	—	Only include a data point the user explicitly asked for.

`get_clay_mcp_task_context`

Read Clay enrichment results · read-only · open-world Read enrichment results for a prior find_clay_mcp_company or find_clay_mcp_contacts_at_company call, by its task_id. NEVER tell the user data wasn’t found without calling this first — the initial search response only has base fields. Response shape: contacts are a top-level contacts array (NOT nested under companies); each contact’s requested enrichments (e.g. Email) appear in its own enrichments array as {name, state, value} — check state == "completed" and read value, don’t look for a plain top-level email field. If state isn’t "completed" yet, poll again rather than answering with missing data.

Parameter	Type	Required	Default	Description
`task_id`	string ≥ 1	Yes	—	The task_id returned by an earlier find call.
`entity_ids`	string[]	—	—	Optional: only these entity ids. Leave unset for all entities.
`page`	integer ≥ 1	—	—	1-based page of entities (100/page). Ignored if entity_ids is set.

Stage Requirements

Discover and propose deterministic entry requirements for a CRM pipeline stage — read the connected pipeline’s stages, existing requirements and revision history, then propose a new or updated requirement for the user to confirm on a review card. Group id: stage-requirements.

`list_stage_requirement_stages`

List Stage Requirement Stages · read-only List the stable attribute id and every option (id/value/label/outcome/is_terminal) that Stage Requirements can govern for one object type — the connected CRM’s imported pipeline stages, or native Morphic Deal Stage options. Call this BEFORE propose_stage_requirement to resolve stage_attribute_id and target_option_id; defaults to deals/deal_stage.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	—	`"deals"`	Object type whose pipeline to read. Slugs are PLURAL — ‘deals’, not ‘deal’. Call list_entity_types for custom types.
`attribute_slug`	string	—	`"deal_stage"`	The stage field on that object type. Defaults to the standard ‘deal_stage’; call get_entity_type_schema if the workspace renamed it.

`list_stage_requirement_policies`

List Stage Requirement Policies · read-only List every Stage Requirement policy on an object type — status (active/disabled_*), which stage value it governs, and its revision count. Use this to answer ‘what requirements exist today’ or to find the policy_id a ‘change’ or ‘disable’ request refers to.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	—	`"deals"`	Object type whose policies to list. Slugs are PLURAL — ‘deals’, not ‘deal’.

`get_stage_requirement_revision_history`

Get Stage Requirement Revision History · read-only List every immutable revision of one Stage Requirement policy (revision number, plain-language summary, created_at) — use this to explain how a requirement has changed over time.

Parameter	Type	Required	Default	Description
`policy_id`	string	Yes	—	Policy whose revision history to read — the id returned by list_stage_requirement_policies.

`list_stage_requirement_activity_types`

List Stage Requirement Activity Types · read-only List the canonical activity types (meeting/call/email/task) and states (logged/completed) an activity requirement leaf can use. Call this if unsure of the exact vocabulary. Parameters: none

`propose_stage_requirement`

Propose Stage Requirement Validate and canonicalize a Stage Requirement proposal — activates NOTHING. Resolve every schema id yourself first (list_stage_requirement_stages for stage_attribute_id/target_option_id, get_entity_type_schema for field/relation attribute ids) — never guess an id. If a field the user wants doesn’t exist yet, create it first (create_attribute) and confirm that, THEN call this. On success, call present with type=‘stage_requirement_review’ and this tool’s returned body PASSED THROUGH VERBATIM, unmodified — do not re-describe it in markdown. The user confirms or declines the card directly; there is no separate activation tool. Web channel only.

Parameter	Type	Required	Default	Description
`object_type_id`	string	Yes	—	From list_entity_types / resolveObjectTypeId, never guessed.
`stage_attribute_id`	string	Yes	—	From list_stage_requirement_stages.
`target_option_id`	string	Yes	—	From list_stage_requirement_stages — the specific stage value this requirement gates entry into.
`action`	`activate` \| `disable`	Yes	—	‘activate’ proposes a new/replacement requirement tree. ‘disable’ turns an existing requirement off — ‘root’ is not needed.
`root`	object	—	—	Required when action=‘activate’. The full requirement tree.
`source_text`	string 1–2000	Yes	—	The user’s own words asking for this, quoted or lightly trimmed — never a fabricated paraphrase. Stored in the audit trail.

`scan_stage_requirement_violations`

Scan Stage Requirement Violations · read-only For the opt-in Stage Requirement Violations monitoring routine ONLY. Returns every deal still failing an accepted violation (a provider-sync or import write that landed despite not meeting a requirement) — a deal drops off this list automatically once it leaves the stage, is overridden, or becomes compliant, so this tool never needs a prior-run cursor. If the routine’s object type is connected to a CRM, refresh that CRM’s pipeline first (sync_linked_record or the equivalent refresh tool) so results reflect the latest inbound state — this tool does not fetch provider data itself. Report the list to the user; do not judge compliance yourself.

Parameter	Type	Required	Default	Description
`object_type_slug`	string	—	`"deals"`	Restrict the scan to one object type. Defaults to deals.

Workspace

Identify the current user, list workspace members, and read workspace-level configuration. Group id: workspace.

`get_current_user`

Get Current User · read-only Who is making this request: their name, Morphic user_id, and whether they’re linked to a CRM contact record. Use the returned user_id directly as assignee_user_id when they ask you to assign something to themselves (‘assign it to me’). They are a WORKSPACE MEMBER (staff), not a CRM contact — never search the CRM to identify them. If requester is null this caller’s identity isn’t known; ask who they are rather than guessing. Parameters: none

`list_workspaces`

List Workspaces · read-only Workspaces this connection may reach. Use the returned slug in ?workspace=<slug> on the connect URL when the user belongs to more than one and has not named one. These are Morphic team workspaces, not CRM records. Parameters: none

`list_workspace_members`

List Workspace Members · read-only List the members of this workspace with their user_id, name, and email. Use this to resolve a TEAMMATE’s name to a user_id before calling create_activity/update_activity with assignee_user_id. Call this FIRST when the user says create / assign / add / make a task for a named person — before ask_context or search_entities. These are workspace members (staff) — a different thing from CRM contacts/people, which have their own entity ids and are never valid assignees. For the person currently talking to you, use get_current_user instead of scanning this list.

Parameter	Type	Required	Default	Description
`limit`	integer 1–500	—	`100`	Maximum members to return, 1–500. Defaults to 100; the response sets `truncated: true` and `total` when the workspace has more, so raise this only if you actually need the rest.

`list_task_statuses`

List Task Statuses · read-only List task status slugs configured for this workspace (label, slug, whether it counts as completed). Call this before create_activity/update_activity when setting status — only these slugs are valid (typically not_started, in_progress, completed, cancelled, plus any custom statuses). Never invent slugs like pending.

Parameter	Type	Required	Default	Description
`include_inactive`	boolean	—	`false`	Include disabled statuses (default: active only)
`limit`	integer 1–200	—	`100`	Maximum statuses to return, 1–200. Defaults to 100; the response sets `truncated: true` and `total` when the workspace has more.

Task Suggestions

Review and accept the agent-generated task suggestions queued for the workspace. Group id: tasks.

`list_task_suggestions`

List Task Suggestions · read-only List AI-generated task suggestions for a specific CRM entity. These are suggested next actions inferred from ingested emails, meetings, and signals.

Parameter	Type	Required	Default	Description
`entity_type`	string	Yes	—	Object type slug of the entity, e.g. ‘people’, ‘companies’, ‘deals’. Workspaces can define custom types — call list_entity_types for the full set rather than guessing.
`entity_id`	UUID	Yes	—	Entity UUID to get suggestions for
`status`	string	—	`"suggested"`	Suggestion lifecycle state: ‘suggested’ (default, not yet acted on), ‘accepted’, or ‘dismissed’
`page`	integer ≥ 1	—	`1`	1-based page number. Defaults to 1 (first page).
`page_size`	integer 1–50	—	`10`	Items per page, 1–50. Defaults to 10; raise it rather than paging repeatedly.

`accept_task_suggestion`

Accept Task Suggestion · idempotent Accept one AI-generated suggestion from list_task_suggestions, converting it into a real task activity linked to the same entity and marking the suggestion accepted. Use this whenever the user approves a suggestion; use create_activity for a task the user described themselves, which has no suggestion behind it.

Parameter	Type	Required	Default	Description
`suggestion_id`	UUID	Yes	—	Task suggestion UUID to accept, from list_task_suggestions
`due_date`	string	—	—	Optional ISO8601 due date to assign to the created task

Web Search

Search the public web and fetch page content for research that goes beyond workspace data. Group id: search.

`web_search`

Web Search · open-world Search the web for current information, news, or external data. This is the DEFAULT web search tool — prefer it over parallel_search. Use it when you need up-to-date, factual, or publicly available information that is not in the CRM or workspace. COST: each call consumes workspace credits, so call it only when the answer genuinely requires external information — do not call it speculatively, and do not repeat a near-identical query. Prefer mode=quick|standard|deep (deeper modes cost more). Optional output_schema enables synthesized output. Returns title, URL, snippet, published date, and optional synthesized output.

Parameter	Type	Required	Default	Description
`query`	string 1–500	Yes	—	Natural language research query for the web
`num_results`	integer 1–10	—	`5`	Number of search results to return (1-10)
`mode`	`quick` \| `standard` \| `deep`	—	`"standard"`	Product intent: quick, standard (default), or deep
`search_type`	`auto` \| `fast` \| `instant` \| `deep-lite` \| `deep` \| `deep-reasoning`	—	—	Advanced Exa type override. Prefer mode for normal use.
`contents_mode`	`highlights` \| `text` \| `highlights_and_text`	—	—	Advanced contents override; defaults from mode policy
`system_prompt`	string ≤ 4000	—	—	Optional instructions guiding synthesis and deep-search planning
`output_schema`	object	—	—	Optional JSON Schema for synthesized Exa output.content

Paid Add-ons

Marketplace add-ons billed separately and usable only once installed for the workspace: Parallel Search, Flint and AgentMail. Group id: addons.

`parallel_search`

Parallel Search (paid add-on) · read-only · open-world Search the web using Parallel Search — a paid add-on tool. Must be installed via Marketplace → Add-ons before use. DO NOT use this as your default web search: use web_search for web lookups. Only use parallel_search when (a) the user specifically asks for Parallel / Parallel Search by name, or (b) web_search already ran and returned nothing usable for this query. Never call both for the same question as a matter of course.

Parameter	Type	Required	Default	Description
`query`	string 1–500	Yes	—	Search query
`num_results`	integer 1–10	—	`5`	Number of results to return (1-10)

`flint_action`

Flint (paid add-on) · destructive · open-world Perform a WRITE action in Flint — a paid add-on that builds/updates live landing pages and manages connected ad accounts. Must be installed via Marketplace → Add-ons before use. WHEN TO CALL: only when the user explicitly names Flint, or explicitly asks you to create/change a landing page or an ad/ad-account setting. If the request is ambiguous, ask first — do not infer it. NEVER call this to answer a question, to look something up, to check status, or to see what Flint would do. It has no read-only mode: every call makes a real external change (a page published or edited, ad spend or targeting altered) that is visible outside this workspace and may not be undoable. Repeating a call can duplicate the change.

Parameter	Type	Required	Default	Description
`instruction`	string 1–2000	Yes	—	Natural-language instruction describing the change Flint should make (e.g. ‘create a landing page for the Q3 webinar with a signup form’, ‘pause the Google Ads campaign named Retargeting-EU’). State the intended change explicitly — this is executed, not previewed. Do not phrase it as a question.

`agentmail_action`

AgentMail (paid add-on) · destructive · open-world Send, list, or read email through the agent’s own AgentMail inbox — paid add-on, must be installed via Marketplace → Add-ons. ACTIONS and their payload keys: • send — DELIVERS A REAL EMAIL to real recipients immediately. payload: { to: string[] (or a single address string, required), subject: string, body: string (alias: text), cc?: string[] | string }. Only call after the user has explicitly approved sending, and echo the recipients and subject back to them first. There is no undo. • list_messages — list messages in the inbox. payload: { limit?: number }. • read_message — fetch one message. payload: { message_id: string }. list_messages and read_message are not implemented on the backend yet and currently return error_code ‘not_implemented’. Do NOT use this to draft emails for chat. For drafts, write To/Subject/Body in your reply; the web UI shows an editable card automatically.

Parameter	Type	Required	Default	Description
`action`	`send` \| `list_messages` \| `read_message`	Yes	—	Operation to perform. ‘send’ delivers a real email immediately — requires explicit user approval. ‘list_messages’ and ‘read_message’ are reads.
`payload`	object	—	`{}`	Arguments for the chosen action. send: { to, subject, body, cc? }. list_messages: { limit? }. read_message: { message_id }. See the tool description for exact types.

​Groups

​Diagnostics

​ping

​Context

​ask_context

​get_context

​Schema

​list_entity_types

​get_entity_type_schema

​Records

​present_crm_card

​list_entities

​get_entity

​get_entity_with_relations

​create_entity

​update_entity

​set_entity_field

​link_entities

​search_entities

​pipeline_overview

​archive_entity

​delete_entity

​bulk_update_entities

​bulk_archive_entities

​bulk_delete_entities

​unlink_entities

​bulk_link_entities

​bulk_unlink_entities

​Activities

​list_activities

​get_activity

​create_activity

​update_activity

​archive_activity

​unarchive_activity

​delete_activity

​bulk_create_activities

​bulk_update_activities

​bulk_archive_activities

​bulk_delete_activities

​complete_task

​Notes

​list_notes

​create_note

​update_note

​bulk_create_notes

​bulk_delete_notes

​delete_note

​Knowledge Base

​list_kb_documents

​search_kb_documents

​get_kb_document

​create_kb_document

​update_kb_document

​get_workspace_context

​Wiki

​wiki_search

​wiki_write

​wiki_append

​wiki_edit_section

​wiki_list

​Memory

​morphic_recall

​morphic_attachment_recall

​morphic_remember

​Calendar

​list_calendar_events

​get_calendar_event

​get_calendar_connection_status

​create_calendar_event

​update_calendar_event

​delete_calendar_event

​Meetings

​list_meetings

​get_meeting

​get_meeting_follow_ups

​link_meeting_to_entity

​unlink_meeting_from_entity

​search_meeting_transcripts

​force_join_meeting_bot

Groups

Diagnostics

`ping`

Context

`ask_context`

`get_context`

Schema

`list_entity_types`

`get_entity_type_schema`

Records

`present_crm_card`

`list_entities`

`get_entity`

`get_entity_with_relations`

`create_entity`

`update_entity`

`set_entity_field`

`link_entities`

`search_entities`

`pipeline_overview`

`archive_entity`

`delete_entity`

`bulk_update_entities`

`bulk_archive_entities`

`bulk_delete_entities`

`unlink_entities`

`bulk_link_entities`

`bulk_unlink_entities`

Activities

`list_activities`

`get_activity`

`create_activity`

`update_activity`

`archive_activity`

`unarchive_activity`

`delete_activity`

`bulk_create_activities`

`bulk_update_activities`

`bulk_archive_activities`

`bulk_delete_activities`

`complete_task`

Notes

`list_notes`

`create_note`

`update_note`

`bulk_create_notes`

`bulk_delete_notes`

`delete_note`

Knowledge Base

`list_kb_documents`

`search_kb_documents`

`get_kb_document`

`create_kb_document`

`update_kb_document`

`get_workspace_context`

Wiki

`wiki_search`

`wiki_write`

`wiki_append`

`wiki_edit_section`

`wiki_list`

Memory

`morphic_recall`

`morphic_attachment_recall`

`morphic_remember`

Calendar

`list_calendar_events`

`get_calendar_event`

`get_calendar_connection_status`

`create_calendar_event`

`update_calendar_event`

`delete_calendar_event`

Meetings

`list_meetings`

`get_meeting`

`get_meeting_follow_ups`

`link_meeting_to_entity`

`unlink_meeting_from_entity`

`search_meeting_transcripts`

`force_join_meeting_bot`