Strava MCP Server

@ctvidic

About Strava MCP Server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "strava-mcp-server-ctvidic": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Strava MCP Server?

A Model Context Protocol (MCP) server that provides access to the Strava API, enabling language models to interact with Strava data including activities, athlete information, and more.

How to use Strava MCP Server?

Install Python 3.12+, clone the repository, create a virtual environment, install dependencies, configure a config/.env file with Strava API credentials (Client ID, Client Secret, Refresh Token), then run via Claude Desktop configuration or as an HTTP server. With Claude you can ask natural‑language queries about activities, performance, social interactions, and achievements.

Key features of Strava MCP Server

Activity tracking and analysis
Athlete statistics
Route visualization
Achievement tracking
Social features (kudos, comments)

Use cases of Strava MCP Server

Query recent activities and get detailed run/ride summaries
Analyze personal performance trends (pace, heart rate, elevation gain)
Retrieve social interactions and club activity data
List segment achievements and personal records
Visualize activity route maps and elevation profiles

FAQ from Strava MCP Server

What are the prerequisites?

Python 3.12+, Strava API credentials (Client ID, Client Secret, Refresh Token), and pip.

How do I obtain Strava API credentials?

Go to https://www.strava.com/settings/api, create a new application, and follow the OAuth 2.0 flow to get your refresh token.

What data can I access through Claude?

Activity details (distance, duration, pace, heart rate, power, cadence, splits, weather), athlete statistics, personal records, training load, social kudos and comments, club activities, segment efforts, and route maps with elevation data.

How can I run the server as an HTTP endpoint?

Start the server with ./run_server.sh and access endpoints like GET /activities/recent, GET /activities/{id}, GET /activities/{id}/map, and GET /athlete/stats at http://localhost:8000.

What should I never commit?

The .env file and API credentials; the .gitignore file is configured to prevent sensitive data from being committed.