whoop

The WHOOP MCP Server exposes a set of tools that let Claude Desktop query and retrieve your WHOOP fitness data locally on your machine. It supports retrieving profile information, workouts, recovery metrics, sleep data, and daily physiological cycles, all via natural language prompts. The server keeps all data private on your device, with token management and smart caching to improve responsiveness. Typical interactions include asking for your workout history, checking recovery trends, or querying sleep quality over a date range. The available tools (get_whoop_profile, get_whoop_workouts, get_whoop_recovery, get_whoop_sleep, get_whoop_cycles, get_whoop_auth_status, clear_whoop_cache) enable granular access to distinct data domains and can be combined in follow-up questions for deeper insights.

Prerequisites:

• Python 3.8+
• Claude Desktop
• Active WHOOP account

1. Clone the repository and install dependencies

git clone https://github.com/romanevstigneev/whoop-mcp-server.git
cd whoop-mcp-server
pip install -r requirements.txt

2. Run the interactive setup (optional) or configure OAuth manually

python setup.py

 - Interactive setup will open a browser for WHOOP OAuth authorization and securely save tokens locally, producing Claude Desktop configuration.
 - If interactive setup fails, use the manual steps described in the README to obtain tokens and verify setup using the included Python scripts.

3. Configure Claude Desktop (example, update paths to your environment)

{
  "mcpServers": {
    "whoop": {
      "command": "/path/to/python3",
      "args": ["/path/to/whoop-mcp-server/src/whoop_mcp_server.py"],
      "env": {
        "PYTHONPATH": "/path/to/whoop-mcp-server/src"
      }
    }
  }
}

4. Restart Claude Desktop to load the new MCP server configuration.

Notes:

• If you use the Smithery hosted option, follow the Smithery README to deploy and skip local installation steps.
• Ensure you replace placeholder paths with real locations on your system.

Tips and troubleshooting:

• Ensure Python path in the environment matches your Python installation; the README emphasizes using the full Python path (e.g., /usr/bin/python3).
• Tokens are stored locally and encrypted; verify file permissions (600) for token files.
• If you encounter OAuth issues, re-run the interactive setup or re-authorize via the manual steps described in the README.
• The server caches data for improved performance; if data seems stale, use clear_whoop_cache to force fresh API calls.
• Optional environment variables include LOG_LEVEL and LOG_FILE to control logging verbosity and location.