Tools Reference

The Agents MCP server exposes 20 tools, plus two meta-tools for chaining calls. Every project-scoped tool takes a project_id argument, always call whoami first to get it. Each tool maps to one endpoint in the Agents REST API; the REST path is listed with each tool (all paths are under /api/v1/business).

​

Common arguments

---

​

Identity & project

​

whoami

Return the caller’s identity, HQ teams, and the projects in the active workspace. Call this first: every project-scoped tool needs a project_id, and you get it here. GET /whoami

​

list_project_resources

List a project’s reference resources by resource: users, labels, settings, skills, or agents. Pass the id whoami returned for you as resource_id to fetch your own project-scoped record (for example, your role in the project). POST /project-resources/query

---

​

Tasks

​

query_tasks

Query the project’s tasks. view="list" returns a cursor page of task list items (with filter, sort, and pagination); view="counts" returns totals grouped by group_by (status, priority, assignee, or creator). POST /tasks/query

​

get_task

Get one task with full detail, attachments and labels are always included. Pass include to also fetch the task’s timeline, relations, and/or approvals. GET /tasks/{task_id}

​

create_task

Create a task in the project. Purely additive: nothing is overwritten, and the task is visible and deletable in the product. POST /tasks

​

update_task

Update a task: edit fields (action="update_fields"), transition its status (action="transition_status"), or (re)assign it (action="assign"). All changes are reversible. POST /tasks/update

​

comment_on_task

Create a comment on a task (action="create"). A reversible authoring action. POST /tasks/comments

---

​

Agent runs

​

get_agent_runs

Get agent-run history for a task or an agent, or step-by-step progress for a single run. Scope task_runs needs task_id; agent_runs needs agent_id; run_progress needs task_id and run_id. POST /agent-runs/query

---

​

Playbooks

​

list_workflows

List the project’s playbooks or their status counts. Use view="list" for the paginated inventory (filter by type, status, or search) or view="counts" for totals. POST /workflows/query

​

get_workflow

Get one playbook and its related data. view selects the slice: detail, versions, version_detail (needs version_id), runs (filter by run status or search), or run_detail (needs workflow_run_id). POST /workflows/get

​

list_workflow_components

List playbook building blocks. view="components" is the catalog, view="batch" fetches by capability_ids, and view="hub_capabilities" lists the workflows-hub capabilities. POST /workflows/components

---

​

Grids

​

list_grids

List a project’s grids, or read one grid’s detail or processing status, via the view enum (detail and status need grid_id). view="column_options" is the live catalog of column types you can add. POST /grids/query

​

get_grid_data

Read a grid’s columns, rows, a single cell, a cell’s run detail, or search rows via the view enum. A playbook column’s workflow_version_id (from view="columns") names its pinned version, pass it to get_workflow (view="version_detail"). POST /grids/data

---

​

Knowledge & brand

​

search_knowledge

Semantic search over the project’s knowledge sources (RAG). Returns the matched chunks and, when generate_answer is true, a generated answer; set it false for raw chunks only. Optionally scope the search to specific sources. POST /knowledge/search

​

get_knowledge_source

List the project’s knowledge sources, list its folders, or fetch one source’s content. Does not cover the Brand Kit, that’s a separate resource fetched with get_brand_kit. POST /knowledge/sources

​

get_brand_kit

Get the project’s brand kit. view="catalog" lists the available brand-kit section names only; use it to answer “what sections does my brand kit have.” Other views compose the full section content. POST /brand-kit

---

​

Content intelligence

​

get_ci_dashboard

Project-level content-intelligence reads: page summary, live summary, available filters, countries, the ranked page list, page groups, and the page-list column scope, selected by view. view="pages" is also how you resolve a page name or URL to a page_id. POST /content-intelligence/dashboard

​

get_page_report

Per-page content-intelligence report selected by report_type (SEO, AI citations, funnels, traffic, SERP, keywords, lifecycle, activity). Some reports require market_id. Resolve page_id from get_ci_dashboard (view="pages"). POST /content-intelligence/page-report

---

​

Integrations & attachments

​

list_integrations

List the workspace’s connected apps and integration connections. view="apps" returns the app catalog; view="apps_overview" groups connections by app with active/inactive counts; view="connections" lists individual connections. POST /integrations/query

​

download_attachment

Get a short-lived presigned download URL for a task or comment attachment. Returns the URL plus filename and content type, not the file bytes. For a task attachment, pass task_id. POST /attachments/download-url

---

​

Meta-tools (MCP only)

These two tools have no REST equivalent, they orchestrate the tools above in a single request.

​

execute_batch

Run up to 10 linear tool calls in one request, passing results between steps. Use it for chains with no loops or conditionals.

​

execute_plan

Run server-side TypeScript (“code mode”) for plans that need loops, conditionals, or three-plus calls with intermediate data shaping. Never use it to skip resolving which project you mean.