A Model Context Protocol (MCP) server connects the Strava API to Large Language Models (LLMs), specifically targeting users of Claude Desktop or Claude Code. It empowers users to query, analyze, and interact with their Strava fitness data using natural language, simplifying access to insights on progress, workouts, routes, and performance metrics.

How It Works

The server acts as an intermediary, translating conversational prompts directed at an LLM into actionable Strava API requests. Upon connecting a Strava account via OAuth, the LLM can ask questions like "How far did I run this month?" or "Analyze my last ride." The MCP server fetches the relevant data, processes it, and returns structured information to the LLM for a natural language response. This approach abstracts the complexity of direct API interaction, making Strava data accessible through intuitive dialogue.

Quick Start & Requirements

• Primary Install/Run: Recommended: npx -y @r-huijts/strava-mcp-server. Alternative: npm install -g @r-huijts/strava-mcp-server.
• Prerequisites: Claude Desktop or Claude Code, Strava API credentials (Client ID, Client Secret from strava.com/settings/api).
• Setup: Configure Claude Desktop/Code with the MCP server details, restart Claude, and then connect your Strava account via the browser-based OAuth flow.
• Links: README, GitHub repository (implied by source build instructions).

Highlighted Details

• Enables natural language querying for tracking progress, analyzing workouts, exploring routes, and gaining coaching insights from Strava data.
• Seamless integration with Claude LLM environments via the Model Context Protocol (MCP).
• Features an optimized, compact data format for activity streams (~70-80% smaller), with options for smart chunking and downsampling suitable for LLM processing.
• Includes automatic Strava token refresh and local credential persistence.

Maintenance & Community

Contributions are welcomed via Pull Requests, and questions can be directed to GitHub issues. No specific community channels (e.g., Discord, Slack) or notable contributors are mentioned in the README.

Licensing & Compatibility

The project is released under the MIT License, which is permissive for commercial use and integration into closed-source applications.

Limitations & Caveats

The project is primarily designed for integration with Claude LLM environments. Users must obtain and configure Strava API credentials. While robust, the troubleshooting section indicates potential setup complexities related to authentication and connection.