Docs · MCP tools
MCP tools
Some facts only the agent has: what the session is really about, which repo it moved into,
which branch the work merges into. Rather than scrape that out of the pane, the manager ships
an MCP server in the same binary (agent-manager mcp, stdio) and registers it into
every session it spawns or revives, so these arrive as native tools with descriptions telling
the agent when to call each.
The tools
| Tool | What the agent uses it for |
|---|---|
| rename | Names its own session once it knows what the work is, replacing the placeholder. |
| review_repo | Declares the repo or worktree it moved into. The path is validated as a git root, so review opens on the right one. |
| review_base | Declares the ref its branch diffs against, validated in that repo and stored per session and repo. |
| review_mode | Sets the scope review opens on, for example switching to staged just before it commits. |
Registration
Registration is per tool and automatic. The built-in tools register on their own:
| Tool | How it is registered |
|---|---|
| claude | A generated --mcp-config file. |
| codex | -c mcp_servers… overrides on the command line. |
| opencode | An OPENCODE_CONFIG merge file. |
| grok, gemini | A one-time mcp add --scope user entry on first launch. |
A tool you added yourself opts in, or out, in its config block:
config.toml
[tools.mytool]
mcp = "claude" # or codex, opencode, grok, gemini, none
One server, every session
The stdio server serves whichever session called it, identified through its environment, so
there is nothing per-session to launch or clean up. No prompt injection, no per-project setup.
The same thing from a shell
The subcommands keep working everywhere, MCP or not, so an agent that speaks no MCP can still run one shell command:
Terminal
agent-manager rename "auth token refresh"
agent-manager review-repo /path/to/repo
agent-manager review-base main
agent-manager review-base --clear