Orchid1970/fitness-health-mcp

Fitness & Health MCP Server

A Model Context Protocol (MCP) server that aggregates data from multiple fitness and health tracking services into a unified interface.

Supported Services

• Peloton - Cycling and fitness workouts
• Nike Run Club - Running activities (limited support)
• Withings - Health metrics (weight, heart rate, blood pressure)
• Apple HealthKit - Comprehensive health data via XML export
• Sleep Number - Sleep tracking (placeholder)
• Hydrow - Rowing workouts (placeholder)

Features

• 🏋️ Unified Workout Aggregation - Get all workouts across platforms
• 😴 Sleep Data Synthesis - Combine sleep data from multiple sources
• 📊 Health Metrics - Track weight, heart rate, and other vitals
• 🔐 OAuth2 Support - Secure authentication for supported services
• 📈 Health Summary - Comprehensive overview of your fitness data

Installation

1. Clone this repository:

git clone https://github.com/Orchid1970/fitness-health-mcp.git
cd fitness-health-mcp

2. Install dependencies:

pip install -r requirements.txt

3. Configure your services:

cp config.example.json config.json
# Edit config.json with your API credentials

Configuration

Peloton

• Uses username/password authentication
• No API key required
• Call peloton_login tool with credentials

Withings

1. Register your application at Withings Developer Portal
2. Get your client_id and client_secret
3. Add them to config.json
4. Use authorize_service tool to start OAuth flow

Apple HealthKit

1. Export your health data from iPhone:
   • Health app → Profile → Export All Health Data
2. Extract the export.xml file
3. Provide the path when calling tools

Nike Run Club, Sleep Number, Hydrow

• These services have limited or no public API
• Placeholder implementations provided
• Community contributions welcome!

Usage

Running the Server

python server.py

The server will start and listen for MCP protocol messages via stdio.

Available Tools

get_all_workouts

Aggregate workouts from all connected services.

{
  "days": 7,
  "services": ["peloton", "nike_run", "hydrow", "apple_healthkit"]
}

get_all_sleep_data

Get sleep data from Sleep Number and Apple HealthKit.

{
  "days": 7
}

get_health_metrics

Retrieve health metrics from Withings.

{
  "days": 30
}

get_peloton_workouts

Get Peloton-specific workouts.

{
  "limit": 10
}

peloton_login

Authenticate with Peloton.

{
  "username": "your_email@example.com",
  "password": "your_password"
}

authorize_service

Start OAuth flow for Withings.

{
  "service": "withings"
}

get_health_summary

Get comprehensive health and fitness summary.

{
  "days": 7
}

Deploying to SimTheory.ai

1. Push to GitHub (already done!)
2. Connect to SimTheory.ai:
   • Go to SimTheory.ai MCP settings
   • Add GitHub MCP server
   • Point to: https://github.com/Orchid1970/fitness-health-mcp
3. Configure credentials via environment variables or config file
4. Start using the tools in your AI conversations!

Project Structure

fitness-health-mcp/
├── server.py              # Main MCP server
├── requirements.txt       # Python dependencies
├── config.example.json    # Example configuration
├── README.md             # This file
└── services/             # Service connectors
    ├── __init__.py
    ├── base.py           # Base connector class
    ├── peloton.py        # Peloton integration
    ├── nike_run.py       # Nike Run Club (placeholder)
    ├── withings.py       # Withings OAuth2
    ├── apple_healthkit.py # Apple HealthKit XML parser
    ├── sleepnumber.py    # Sleep Number (placeholder)
    └── hydrow.py         # Hydrow (placeholder)

Development

Adding a New Service

1. Create a new file in services/ (e.g., garmin.py)
2. Extend the ServiceConnector base class
3. Implement required methods:
   • authorize() - Start auth flow
   • get_workouts() - Fetch workout data
   • get_sleep() - Fetch sleep data (if applicable)
4. Add connector to server.py
5. Add tools for the new service

Testing

# Test individual connectors
python -c "from services.peloton import Connector; c = Connector({}); print(c.authorize())"

Security Notes

• Never commit API keys or passwords to the repository
• Use environment variables for sensitive data
• Review each service's terms of service
• Some services (Nike, Sleep Number) may require unofficial methods

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Add your changes
4. Submit a pull request

Priority areas:

• Implementing Nike Run Club integration
• Adding Sleep Number support
• Hydrow API integration
• Additional health services (Garmin, Fitbit, etc.)

License

MIT License - See LICENSE file for details

Support

For issues or questions:

• Open a GitHub issue
• Contact: Timothy Escamilla

Roadmap

• Complete Nike Run Club integration
• Add Garmin Connect support
• Implement data caching
• Add data visualization tools
• Create web dashboard
• Add export to CSV/JSON
• Implement data sync scheduling

Built with ❤️ for unified health and fitness tracking