Filesystem-based, database-free work-claiming and coordination locks for AI coding agents (Claude Code and friends) working across multiple git worktrees of the same repository, exposed as an MCP stdio server.
Five tools with complete schemas, strong descriptions (avg 280 chars), and proper parameter typing. All tools have clear verb-noun naming (lock_query, lock_create, lock_update, lock_finish, lock_check_conflict). Tool annotations present (readOnlyHint, idempotentHint, openWorldHint). Error handling returns actionable messages (e.g., TaskNotFoundError lists actual task texts). Main gaps: no pagination support for lock_query results (could return hundreds of locks), output schema not formally documented in code, and lock_finish lacks dry-run/confirmation pattern for irreversible operations.
Checks whether any currently ACTIVE lock claims file(s)/path(s) that overlap the glob patterns you pass in. This tool is purely INFORMATIONAL — it never blocks, refuses, or vetoes anything; it has no side effects and cannot prevent lock_create from proceeding. It exists only to give you information so you (the calling agent) can decide for yourself whether to proceed, coordinate with the other lock's owner, or pick a narrower scope. Overlap is determined by a static-prefix glob heuristic (not exact set intersection) that is intentionally biased toward reporting overlaps that turn out not to matter, rather than missing a real one — see this project's README for the exact heuristic and a documented case (filesystem case-sensitivity) it deliberately does not catch. Returns the same compact summary shape as lock_query for every overlapping active lock (empty array if none).
Claims a piece of work by writing a new active lock file. Use this after you have decided to proceed (optionally having checked lock_query / lock_check_conflict first). tasks are created as a plain unchecked checklist; call lock_update as you complete each one. agent_id / parent_agent_id: pass your OWN id here only if you already know it from your own context (some orchestration harnesses hand a subagent an explicit id when dispatching it) — this server has no way to detect either value automatically (no MCP transport mechanism exposes a session/agent id to a stdio server subprocess). Omit them (or pass null) if you do not know them; they will be recorded as null, never fabricated. parent_agent_id specifically means "the id of whatever spawned you," if you are a subagent and happen to know it.
Marks an active lock as done and moves it out of the active set into the done archive. After this call, lock_query's default view (status omitted) will no longer show this lock — you must explicitly pass status: "done" or status: "all" to see it. Optionally append a final summary note. This is the only way to remove a lock from the active view; there is no delete operation.
lock_query lacks pagination (limit/offset/cursor). No documented result cap. Large repos could return hundreds of locks, exhausting context window.
Output schema not formally documented in code. Descriptions mention return shape {id, title, status, percentComplete, scope, agent_id, parent_agent_id} but no JSON Schema definition visible for tool responses.
lock_finish (irreversible operation) has no dry-run, confirmation, or undo mechanism. Agents could accidentally archive locks without recovery path.
lock_update requires exact task text match with no fuzzy matching. Error message lists actual tasks, but no guidance on how to discover tasks before calling (agents must call lock_query first).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 64 | 2026-07-28+ | v2 |
Lists agent-locks work-claim locks for the current git repository (shared across all its worktrees). IMPORTANT: when `status` is omitted, this ONLY returns active locks — done/finished locks are excluded from the default view by design, so you see what is currently being worked on, not a full history. Pass status: "done" or status: "all" to include finished locks. Returns a compact summary per lock: {id, title, status, percentComplete, scope, agent_id, parent_agent_id}. percentComplete is computed from the ratio of checked to total tasks on that lock (a lock with zero tasks reports 100).
Flips one task on an existing lock to done or not-done, and optionally appends a note. Call this AS SOON as a task actually completes — not batched at the end of your work — so other agents watching lock_query see live progress. task_text must match an EXISTING task's text EXACTLY (no fuzzy/partial matching); if it does not match, this returns an error listing the lock's actual task texts rather than silently doing nothing. Works on a lock in either active or done status (found by lock_id regardless of which directory it currently lives in).
agent_id and parent_agent_id parameters in lock_create are nullable but no guidance on what happens if agent passes wrong/fabricated IDs. No validation or sanitization visible.