what is Strava MCP Server?
Strava MCP Server is a Model Context Protocol (MCP) server designed to interact with the Strava API, allowing users to access and manage their Strava data.
how to use Strava MCP Server?
To use the Strava MCP Server, clone the repository, install the necessary dependencies, set up your Strava API credentials, and run the server using Python.
key features of Strava MCP Server?
- Retrieve user's activities from Strava
- Get detailed information about specific activities
- Access segments of activities
- View leaderboards for segments
use cases of Strava MCP Server?
- Analyzing personal fitness activities over time.
- Comparing performance on specific segments with friends.
- Integrating Strava data into other applications for enhanced insights.
FAQ from Strava MCP Server?
- What are the prerequisites for using Strava MCP Server?
You need Python 3.13 or later and valid Strava API credentials.
- How do I run the server?
You can run the server by executing
python main.py
in your terminal.
- Can I run the server in development mode?
Yes, you can run it in development mode using the MCP CLI with the command
mcp dev main.py
.
Strava MCP Server
A Model Context Protocol (MCP) server for interacting with the Strava API.
User Guide
Installation
You can easily install Strava MCP with uvx
:
uvx strava-mcp
Setting Up Strava Credentials
-
Create a Strava API Application:
- Go to https://www.strava.com/settings/api
- Create a new application to obtain your Client ID and Client Secret
- For "Authorization Callback Domain", enter
localhost
-
Configure Your Credentials: Create a credentials file (e.g.,
~/.ssh/strava.sh
):export STRAVA_CLIENT_ID=your_client_id export STRAVA_CLIENT_SECRET=your_client_secret
-
Configure Claude Desktop: Add the following to your Claude configuration (
/Users/<username>/Library/Application Support/Claude/claude_desktop_config.json
):"strava": { "command": "bash", "args": [ "-c", "source ~/.ssh/strava.sh && uvx strava-mcp" ] }
Authentication
The first time you use the Strava MCP tools:
- An authentication flow will automatically start
- Your browser will open to the Strava authorization page
- After authorizing, you'll be redirected back to a local page
- Your refresh token will be saved automatically for future use
Available Tools
Get User Activities
Retrieves activities for the authenticated user.
Parameters:
before
(optional): Epoch timestamp for filteringafter
(optional): Epoch timestamp for filteringpage
(optional): Page number (default: 1)per_page
(optional): Number of items per page (default: 30)
Get Activity
Gets detailed information about a specific activity.
Parameters:
activity_id
: The ID of the activityinclude_all_efforts
(optional): Include segment efforts (default: false)
Get Activity Segments
Retrieves segments from a specific activity.
Parameters:
activity_id
: The ID of the activity
Get Segment Leaderboard
Gets the leaderboard for a specific segment.
Parameters:
segment_id
: The ID of the segment- Various optional filters (gender, age group, etc.)
Developer Guide
Project Setup
-
Clone the repository:
git clone <repository-url> cd strava
-
Install dependencies:
uv install
-
Set up environment variables:
export STRAVA_CLIENT_ID=your_client_id export STRAVA_CLIENT_SECRET=your_client_secret
Alternatively, create a
.env
file with these variables.
Running in Development Mode
Run the server with MCP CLI:
mcp dev strava_mcp/main.py
Manual Authentication
You can get a refresh token manually by running:
python get_token.py
Project Structure
strava_mcp/
: Main package directory__init__.py
: Package initializationconfig.py
: Configuration settings using pydantic-settingsmodels.py
: Pydantic models for Strava API entitiesapi.py
: Low-level API client for Stravaauth.py
: Strava OAuth authentication implementationoauth_server.py
: Standalone OAuth server implementationservice.py
: Service layer for business logicserver.py
: MCP server implementation
tests/
: Unit testsstrava_mcp/main.py
: Main entry point to run the serverget_token.py
: Utility script to get a refresh token manually
Running Tests
pytest
Publishing to PyPI
Building the package
# Build both sdist and wheel
uv build
Publishing to PyPI
# Publish to Test PyPI first
uv publish --index testpypi
# Publish to PyPI
uv publish