Strava MCP Server

A Model Context Protocol (MCP) server that connects to the Strava API, allowing AI agents to retrieve athlete stats, list activities, and get detailed activity information.

Prerequisites

Python 3.10+
Strava Account
Strava API Application (to get Client ID and Secret)

Setup

1. Credentials

Go to Strava API Settings.
Create an application if you haven't already.
Note your Client ID and Client Secret.
You need a Refresh Token.
- The easiest way to get one for your own account is to use the Strava OAuth playground or follow the Strava authentication docs to authorize your app and get the initial refresh token.
- Scope required: activity:read_all,read_all (adjust based on needs).

2. Installation

Clone this repository and enter the directory.

Using uv (Recommended):

uv sync
source .venv/bin/activate

Using standard pip:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install .

3. Configuration

Copy .env.example to .env.
Fill in your credentials.

cp .env.example .env
# Edit .env with your favorite editor

Usage

Run the server using fastmcp:

fastmcp run server.py

Or run it directly with Python (if the main block calls mcp.run()):

python server.py

Available Tools

get_athlete_stats: Get statistics for the authenticated athlete.
list_activities: List recent activities (default limit: 5).
get_activity_details: Get detailed information for a specific activity ID.

Development

Modify server.py to add more tools using the stravalib client.

strava-mcp