GitDocket docs
MCP & workflows.
Connect an agent to narrow repository operations, then use the checked-in workflows to guide the work.
Connect over stdio
The @gitdocket/mcp package installs docket-mcp. Configure your MCP client to launch that command with the project repository as its working directory. It resolves the nearest docket.yaml. There is no HTTP MCP endpoint.
For supported coding agents, docket init --agent codex or docket init --agent claude installs the native integration. Other clients use their own stdio server configuration.
The tool surface
These ten tools are captured from the 0.2.1 server. Download the input schemas (JSON), or request tools/list from your installed server for its exact contract.
| Tool | Required input | Purpose |
|---|---|---|
overview | None | Project orientation. |
ready | None | Ready work; optional limit. |
task_list | None | Work items with status/type filters and pagination. |
task_get | id | Full task or epic source. |
search | query | Ranked bundle search. |
source_page | path | Bounded source with a continuation cursor. |
lint | None | Bundle diagnostics. |
task_create | title | Create a task or epic; writes files. |
set_status | id, to | Change stored status; writes files. |
append_log | id, entry | Append a dated work note; writes files. |
Workflow: get oriented
Start with overview. If you need the ready queue, call ready, then inspect a returned ID with task_get. Reading status does not start work.
overview {}
ready {"limit": 5}
task_get {"id": "HBR-4"}Examples show tool names and argument objects, not shell commands. HBR-4 belongs to the synthetic demo; use an ID from your own repository.
Workflow: run a named epic
Ask your agent to run an existing epic through completion. It reads the epic and the repository’s procedure, then works through eligible children, verifies results, and reconciles affected docs.
task_get {"id": "HBR-1"}
source_page {"path": "workflows/docket-epic.md"}If the source is paged, pass the returned nextCursor as cursor with the same path until the procedure is complete. A stale cursor requires restarting the read.
The agent also needs repository editing, Git, and CLI tools. MCP does not itself run an epic. Tracked pickup uses docket task start <ID>; closure follows the close workflow and docket task close <ID>. set_status alone does not perform those procedures.
Workflow: leave a useful handoff
After verifying a change, reconcile the docs and record the outcome with linked commits. Use append_log for a dated note and lint to check the bundle. A new session can use overview and source reads to recover the next step.
Inspectable example
The Harbor welcome guide
A script executed a two-task epic with the real CLI: write a contributor guide, then link it from README and update onboarding. Both tasks and the epic completed; a feedback task became ready next.
The run checked headings, links, recorded Outcomes, and bundle lint. A fresh reader recovered the result from a clean clone. This is a synthetic, scripted example—not a captured agent conversation.