whoop-fitness
Enables users to query WHOOP health data including recovery, sleep, workouts, and cycles through Claude Desktop using MCP tools.
README
WHOOP FastAPI + MCP Server
Full-stack WHOOP integration with FastAPI OAuth server and Model Context Protocol (MCP) server for Claude Desktop.
🚀 Features
- FastAPI OAuth Server - Authenticate with WHOOP and access your health data
- MCP Server - Integrate WHOOP data directly into Claude Desktop conversations
- Complete Data Access - Recovery, sleep, workouts, cycles, and body measurements
- Historical Queries - Access data from specific dates or date ranges
- Secure - OAuth 2.0 authentication with encrypted token storage
📦 What's Included
1. FastAPI Application (whoop_simple.py)
Web server for WHOOP OAuth authentication and data exploration:
- OAuth 2.0 flow with WHOOP API
- Dashboard with health metrics
- REST API endpoints for all WHOOP data
- Token caching for seamless access
2. MCP Server (whoop_mcp_server.py)
Model Context Protocol server for Claude Desktop integration:
- 8 tools for accessing WHOOP data
- Support for historical data queries
- Recovery scores, sleep analysis, workout tracking
- Cycles and strain monitoring
Prerequisites
- Python 3.10+
- VS Code with Python extension (optional)
- HTTPS dev URL (ngrok/cloudflared) for OAuth redirect
- Claude Desktop (for MCP integration)
- WHOOP Developer App credentials from developer.whoop.com
Quick Start
1. Install Dependencies
# Create virtual environment
python -m venv .venv
# Activate it
# Windows:
.venv\Scripts\activate
# macOS/Linux:
source .venv/bin/activate
# Install packages
pip install -r requirements.txt
2. Configure Environment
# Copy template
cp .env.example .env
Edit .env and add your credentials:
WHOOP_CLIENT_ID=your_client_id_here
WHOOP_CLIENT_SECRET=your_client_secret_here
PUBLIC_BASE_URL=https://your-ngrok-url.ngrok-free.dev
3. Setup OAuth Tunnel
# Start ngrok
ngrok http 3000
Copy the HTTPS URL and:
- Update
PUBLIC_BASE_URLin.env - Set callback URL in WHOOP Developer Console to:
https://your-ngrok-url.ngrok-free.dev/callback
4. Authenticate with WHOOP
# Start FastAPI server
python whoop_simple.py
# Open browser to http://localhost:3000
# Click "Click here to login with WHOOP"
# Complete OAuth authorization
Once authenticated, a .token_cache.json file is created with your OAuth token.
5. Try FastAPI Endpoints
http://localhost:3000/dashboard- Health dashboardhttp://localhost:3000/me- Profile + body measurementshttp://localhost:3000/daily?day=YYYY-MM-DD- Daily cycles
6. Setup MCP Server (Optional)
For Claude Desktop integration:
-
Configure Claude Desktop:
Edit
%APPDATA%\Claude\claude_desktop_config.json(Windows) or~/Library/Application Support/Claude/claude_desktop_config.json(Mac):{ "mcpServers": { "whoop-fitness": { "command": "C:\\path\\to\\.venv\\Scripts\\python.exe", "args": ["C:\\path\\to\\whoop_mcp_server.py"] } } } -
Restart Claude Desktop
-
Test in Claude:
- "What's my recovery score today?"
- "Show me my last 7 days of data"
- "How did I sleep last night?"
See docs/SETUP_MCP.md for detailed MCP setup instructions.
📖 Documentation
- QUICKSTART.md - Fast setup and running guide
- SETUP_MCP.md - Complete MCP server setup for Claude Desktop
- MCP_README.md - MCP server documentation and available tools
- ARCHITECTURE.md - System architecture and design
- SECURITY_CHECKLIST.md - Security guidelines for GitHub
🔧 Available MCP Tools
Once configured with Claude Desktop, you can use these tools:
| Tool | Description |
|---|---|
get_user_profile |
Get user profile and basic info |
get_recovery_score |
Latest recovery score with HRV, RHR |
get_current_strain |
Current day strain and heart rate |
get_recent_cycles |
Last 7 days of cycles with recovery |
get_latest_sleep |
Most recent sleep data and stages |
get_recent_workouts |
Recent workout activities |
get_body_measurements |
Height, weight, max heart rate |
get_health_summary |
Complete health overview |
🔐 Security
All sensitive data is protected:
.env- API credentials (in .gitignore).token_cache.json- OAuth tokens (in .gitignore).venv/- Virtual environment (in .gitignore)
Safe to commit and share on GitHub!
🐛 Troubleshooting
FastAPI Issues
- 404 errors: Ensure using
/developer/v2/API base - OAuth callback fails: Verify ngrok is running and URLs match
- No data returned: Check scopes in WHOOP Developer Console include:
read:profileread:body_measurementread:cyclesread:recoveryread:sleepread:workout
MCP Server Issues
- Claude Desktop doesn't see server: Check config file path and restart Claude Desktop
- "No access token found": Authenticate via FastAPI server first (
http://localhost:3000/login) - Tools not appearing: Verify Python path in config points to virtual environment
📝 API Endpoints
FastAPI Server Endpoints
GET /- Home page with linksGET /login- Start OAuth flowGET /callback- OAuth callback handlerGET /me- User profile and measurementsGET /daily?day=YYYY-MM-DD- Cycles for specific dayGET /dashboard- Health dashboard with recent data
🤝 Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test thoroughly
- Submit a pull request
📄 License
MIT License - See LICENSE file for details
🙏 Acknowledgments
- WHOOP API for health data access
- Model Context Protocol (MCP) for AI integration
- FastAPI for the web framework
- Claude Desktop for MCP support
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.