About Strava MCP Server
Strava MCP Server connects MCP-compatible assistants to the Strava API. It supports authenticated activity and segment queries, with browser-based authorization and saved refresh tokens.
Key features
- 01Retrieve user activities with date filters
- 02View detailed activity information
- 03List segments for an activity
- 04Query segment leaderboards
- 05Authorize through browser-based OAuth
Use cases
- 01Review recent Strava activities
- 02Inspect a specific activity and its segments
- 03Check rankings for a Strava segment
MCP support
Exposes Strava API operations as tools for MCP clients, including activity and segment queries. OAuth authorization starts in a browser, and the refresh token is saved for later use.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEStrava 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_secretAlternatively, create a
.envfile 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
License
Acknowledgements
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.