# mighty-mouse-mcp

Source: https://glimind.com/server/pypi%2Fmighty-mouse-mcp
Registry id: `pypi/mighty-mouse-mcp`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "mighty-mouse-mcp": {
      "command": "uvx",
      "args": [
        "mighty-mouse-mcp"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add mighty-mouse-mcp -- uvx mighty-mouse-mcp
```

## Tools (15)

- `agent_execute`: Canonical coding execution with compute scaling support via HostAdapter.solve.
- `compute_scaling_pin`: Pin exact compute scaling configuration for the workspace.
- `compute_scaling_preview`: Preview compute scaling parameters without mutation.
- `compute_scaling_status`: Inspect active compute scaling parameters.
- `policy_pin`: Pin an explicit policy for the workspace.
- `policy_preview`: Preview candidate policy selection without mutation.
- `policy_rollback`: Roll back to the baseline Champion.
- `policy_status`: Inspect the active Champion policy and promotion status.
- `protocol`: Return the versioned low, medium, or high Mighty Mouse protocol.
- `recording_audit`: Check that one exact host task receipt was recorded after it began.
- `run`: Adaptive routing and policy selection for a workspace task.
- `setup_workspace`: Pin an exact local Ollama or host-supplied model identity and MCP execution profile without hand-writing config.
- `swarm_execute`: Execute Multi-Agent Swarm with canonical host provenance and isolated verification via HostAdapter.solve_swarm.
- `verify`: Run tests, lint, build, and optional Git scope checks.
- `verify_and_record`: Run verification and persist a content-free v2 Signal receipt.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.