Strava

This is a Model Context Protocol (MCP) server implemented in TypeScript.

It acts as a bridge between AI assistants and the Strava API, exposing Strava data and functionalities as “tools” that Large Language Models (LLMs) can utilize through the MCP standard.

Features

• 🏃 Access recent activities, profile, and stats
• 📊 Fetch detailed activity streams (power, heart rate, cadence, etc.)
• 🗺️ Explore, view, star, and manage segments
• ⏱️ View detailed activity and segment effort information
• 📍 List and view details of saved routes
• 💾 Export routes in GPX or TCX format to the local filesystem
• 🤖 AI-friendly JSON responses via MCP
• 🔧 Uses Strava API V3

Use Cases

• Personal Fitness Analysis: AI assistants can analyze a user’s recent activities, providing insights on performance trends and suggesting improvements.
• Training Plan Creation: By accessing detailed activity data, AI can create personalized training plans based on the user’s historical performance and goals.
• Route Discovery and Planning: AI can help users find new segments to explore or create custom routes based on their preferences and past activities.
• Performance Tracking: AI can track a user’s progress over time, comparing efforts on specific segments or overall stats across different time periods.

How to Use It

1. Prerequisites:

• Node.js (v18 or later recommended)
• npm (usually comes with Node.js)
• A Strava Account

2. Installation:

   git clone https://github.com/r-huijts/strava-mcp.git
   cd strava-mcp
   npm install
   npm run build

3. Configure Claude Desktop:

   {
     "mcpServers": {
       "strava-mcp-local": {
         "command": "node",
         "args": [
           "/absolute/path/to/your/strava-mcp/dist/server.js"
         ]
       }
     }
   }

4. Strava Authentication Setup:

• Create a Strava API Application at https://www.strava.com/settings/api
• Run the setup script: npx tsx scripts/setup-auth.ts
• Follow the prompts to complete the authentication flow

5. Configure Export Path (Optional): Add ROUTE_EXPORT_PATH to your .env file if you plan to use route export features.

6. Restart Claude Desktop to ensure proper initialization.

7. Use the provided MCP tools in your AI interactions:

• get-recent-activities
• get-athlete-profile
• get-athlete-stats
• get-activity-details
• list-athlete-clubs
• list-starred-segments
• get-segment
• explore-segments
• star-segment
• get-segment-effort
• list-segment-efforts
• list-athlete-routes
• get-route
• export-route-gpx
• export-route-tcx
• get-activity-streams
• get-activity-laps
• get-athlete-zones

FAQs

Q: How often are the access tokens refreshed?
A: The server automatically refreshes the access token when it expires (typically after 6 hours). You only need to run the initial authentication setup once.

Q: Can I use this server with other AI models besides Claude?
A: While designed for Claude, the server follows the MCP standard, so it should be compatible with other AI models that support MCP.

Q: Are there rate limits I should be aware of when using this server?
A: Yes, the Strava API has rate limits. The server doesn’t handle these limits directly, so be mindful of your usage, especially for high-frequency requests.

Q: How can I ensure the security of my Strava data?
A: Always keep your .env file with tokens secure and never share it. Use environment variables for sensitive information and ensure your server is running in a secure environment.