MCP tools
Start the server with pcs mcp, or let pcs connect write the config for you. The server is a thin wrapper over the same core as the CLI, with one tool per core action and a pcs_ prefix, so the CLI and MCP cannot drift apart. Read and write annotations are set on every tool.
Agents should start with pcs_resume.
Tools
| Tool | Purpose |
|---|---|
pcs_resume | Takes over from the previous agent and returns the brief |
pcs_handoff | Writes the handoff |
pcs_status | Current state of the project |
pcs_verify | Checks log integrity |
pcs_session_start | Starts a session. Takes an optional agent name that defaults to --agent |
pcs_session_end | Ends the active session |
pcs_snapshot | Records the repository state |
pcs_task_add, pcs_task_list, pcs_task_update | Tasks |
pcs_note_add, pcs_note_list, pcs_note_resolve | Notes |
pcs_evidence_list | Test runs and other evidence |
pcs_workspace_status | Registered projects |
pcs_test | Runs a command on your machine. Off unless --allow-test is passed |
Restricting the server
| Flag | Effect |
|---|---|
--read-only | Registers only tools that cannot change anything: status, verify, the task, note and evidence lists, and workspace status. Write tools, pcs_resume (it starts a session) and pcs_test are not registered at all, even with --allow-test |
--allow-test | Registers pcs_test. The CLI pcs test stays available to you either way |
--project <path> | Fixes the project. Hosts like Claude Desktop do not control the working directory, so it is not taken from there |
--workspace | Every tool takes an optional project. See Many repositories |
--agent <name> | The default identity for writes |
Starting fails early, on stderr, if the project is not initialised. Nothing but protocol goes to stdout.
Identity
Writes are attributed to the agent argument if given, else the active session’s agent, else the server’s --agent. Agent claims stay reported.
Untrusted content
Recorded content is returned as data, with control characters stripped, and the server
instructions tell the model not to follow it. This reduces, but cannot eliminate, prompt-injection
risk, which is why pcs_test is opt-in.
pcs_test runs commands on your machine, so a prompt-injected agent could abuse it. It is only registered with --allow-test, and an allowlist in the policy file can limit which commands it may run. See Maintenance.
The watcher is not an MCP tool: it is a long-running process you start yourself.