Strava MCP Server

What does “Strava” MCP Server do?

The Strava MCP Server is a Model Context Protocol (MCP) server implemented in TypeScript that seamlessly connects large language models (LLMs) to the Strava API. Acting as a bridge, it enables AI assistants to access, analyze, and interact with a user’s Strava data—including recent activities, profiles, stats, routes, and segments—directly through standardized MCP tools. This integration empowers developers and AI systems to perform tasks such as querying workout stats, fetching activity streams (like power, heart rate, or cadence), exporting routes, and managing segments, all in a secure and AI-friendly manner. By exposing Strava’s rich fitness and activity data as tools, the server enhances development workflows and supports intelligent, data-driven interactions for fitness analysis and coaching.

List of Prompts

No explicit prompt templates were found in the repository.

List of Resources

No explicit resources are documented or exposed in the repository.

List of Tools

• Recent Activities Tool: Access recent Strava activities for the authenticated user.
• Profile Tool: Fetches the profile information for the user.
• Stats Tool: Retrieves running, cycling, and swimming stats.
• Activity Streams Tool: Fetches detailed stream data (heart rate, power, cadence, elevation, etc.) for specific activities.
• Segments Tool: Explore, view, star, and manage Strava segments.
• Routes Tool: List and view details of saved Strava routes.
• Route Export Tool: Export routes in GPX or TCX formats to the local filesystem.

Use Cases of this MCP Server

• Fitness Data Analysis: Developers can integrate the server with LLMs to analyze a user’s workout history, stats, and trends, providing detailed summaries and progress reports.
• Personalized Coaching: AI assistants can provide coaching advice using rich activity data, such as heart rate, power, and cadence streams from recent workouts.
• Route Planning and Exporting: Enables users to list, view, and export their Strava routes for use on GPS devices or for sharing with friends.
• Segment Exploration and Management: Developers can build tools for discovering, starring, and analyzing Strava segments for route optimization and performance benchmarking.
• Club and Community Insights: Access and display club memberships, group activities, and segment leaderboards for enhanced social engagement.

How to set it up

Windsurf

1. Ensure you have Node.js installed.
2. Open the Windsurf configuration file.
3. Add the Strava MCP server package (@r-huijts/strava-mcp@latest) to your MCP servers list.
4. Paste the following JSON snippet into the mcpServers object:

   {
     "strava-mcp": {
       "command": "npx",
       "args": ["@r-huijts/strava-mcp@latest"]
     }
   }
   

5. Save your configuration and restart Windsurf.
6. Verify the setup by checking for Strava MCP tools in your AI assistant.

Securing API Keys Example

{
  "strava-mcp": {
    "command": "npx",
    "args": ["@r-huijts/strava-mcp@latest"],
    "env": {
      "STRAVA_CLIENT_ID": "your-client-id",
      "STRAVA_CLIENT_SECRET": "your-client-secret",
      "STRAVA_ACCESS_TOKEN": "your-access-token"
    }
  }
}

Store credentials securely using environment variables.

Claude

1. Install Node.js as a prerequisite.
2. Open Claude’s configuration file for MCP servers.
3. Add the Strava MCP server using:

   {
     "strava-mcp": {
       "command": "npx",
       "args": ["@r-huijts/strava-mcp@latest"]
     }
   }
   

4. Save the file and restart Claude.
5. Confirm the Strava MCP integration is active.

Cursor

1. Install Node.js if not present.
2. Open the Cursor configuration file relating to MCP servers.
3. Add:

   {
     "strava-mcp": {
       "command": "npx",
       "args": ["@r-huijts/strava-mcp@latest"]
     }
   }
   

4. Save and restart Cursor.
5. Verify functionality within your AI workflows.

Cline

1. Make sure Node.js is installed.
2. Access the configuration file for MCP servers in Cline.
3. Insert:

   {
     "strava-mcp": {
       "command": "npx",
       "args": ["@r-huijts/strava-mcp@latest"]
     }
   }
   

4. Save and restart the Cline environment.
5. Check that Strava MCP tools are discoverable.

Note: Always store sensitive API keys in environment variables, not plain text.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "strava-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “strava-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The Strava MCP Server provides a robust bridge between LLMs and the Strava API, exposing a wide array of tools, with clear documentation and real-world use cases. However, the lack of documented prompt templates and explicit MCP resources limits its out-of-the-box standardization potential. Sampling and Roots support are not mentioned, slightly reducing versatility for advanced MCP scenarios.

MCP Score: 7/10 — a strong, production-ready MCP for Strava integration, with room for improvement in prompt/resource specification and advanced protocol features.

MCP Score