Skip to main content
The product MCP (autonomy) exposes 36 tools, each a thin translation of one platform endpoint. They’re grouped into four domains plus a guidance helper.

Projects

List, connect, and initialize projects.

Tasks

Start, poll, iterate, review, and ship coding tasks.

Setup

Configure commands, env vars, and validation.

Full Mode

Proxy the app’s API calls to your staging backend.

​
Conventions

  • IDs - most tools take a project_id; task tools also take a task_id. Get both from list_projects and list_tasks / get_task.
  • Background work - start_task, continue_task, complete_task, and update_task_env return immediately and run in the background. Poll get_task to track them.
  • Read-only tools are annotated as such and never mutate state (e.g. list_projects, get_task, get_task_pr_diff).

​
Guidance helper

load_autonomy_skill(name) returns a built-in step-by-step playbook - no platform call. Names: setup, full-mode, tasks, troubleshooting. The server also exposes prompts: /autonomy-getting-started, /autonomy-setup, /autonomy-new-task, /autonomy-full-mode.
These reference pages are generated from the MCP server’s tool definitions, so they stay in sync with the code. If a tool’s signature changes, its page changes with it.