About Strava MCP Server
Strava MCP Server connects Claude to an authenticated Strava account. It provides tools for retrieving activities and their details, and for creating manual activities.
Key features
- 01List the athlete’s activities
- 02Retrieve activity details
- 03Create manual activities
- 04View activity kudos and laps
Use cases
- 01Review recent Strava activities
- 02Inspect a run or ride
- 03Create a manual activity
- 04Check kudos or workout laps
MCP support
Exposes Strava activity operations as tools for MCP clients, including retrieving activities, activity details, kudos and laps, and creating manual activities.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
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
This is a Model Context Protocol (MCP) server for the Strava API, allowing Claude to interact with your Strava data.
Features
The Strava MCP server provides the following tools:
get_athlete_activities: Get activities for the authenticated athleteget_activity: Get details of a specific activitycreate_activity: Create a manual activityget_activity_kudoers: Get the athletes who kudoed an activityget_activity_laps: Get the laps of an activity
Setup Instructions
1. Create a Strava API Application
- Go to Strava API Settings
- Create a new application:
- Application Name: Claude Strava Integration (or any name you prefer)
- Website: http://localhost
- Authorization Callback Domain: localhost
- After creating the application, note your Client ID and Client Secret
2. Obtain a Refresh Token
-
Install the required dependencies:
cd /Users/{USERNAME}/Documents/Cline/MCP/strava-mcp-server npm install -
Run the get-strava-token.js script with your Client ID and Client Secret:
node get-strava-token.js YOUR_CLIENT_ID YOUR_CLIENT_SECRET
- The script will open a browser window asking you to authorize the application to access your Strava data.
- After authorization, the script will display your refresh token in the terminal.
3. Configure the MCP Settings
- Update the MCP settings file with your Strava API credentials:
- Location:
/Users/{USERNAME}/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - Add your Client ID, Client Secret, and Refresh Token to the
envsection of thestravaserver configuration:"strava": { "command": "node", "args": [ "/Users/{USERNAME}/Documents/Cline/MCP/strava-mcp-server/dist/index.js" ], "env": { "STRAVA_CLIENT_ID": "YOUR_CLIENT_ID", "STRAVA_CLIENT_SECRET": "YOUR_CLIENT_SECRET", "STRAVA_REFRESH_TOKEN": "YOUR_REFRESH_TOKEN" }, "disabled": false, "autoApprove": [] }
- Location:
4. Build and Start the Server
The server will be automatically started by Claude when needed. If you want to test it manually:
cd /Users/{USERNAME}/Documents/Cline/MCP/strava-mcp-server
npm run build
npm start
Usage Examples
Once the Strava MCP server is configured, you can ask Claude to interact with your Strava data:
- "Show me my recent Strava activities"
- "Get details about my latest Strava run"
- "Create a new manual activity on Strava"
- "Who kudoed my latest Strava ride?"
- "Show me the laps from my last track workout"
Troubleshooting
- Authentication Errors: If you encounter authentication errors, your refresh token may have expired. Run the get-strava-token.js script again to obtain a new refresh token.
- Server Not Starting: Make sure the path to the server in the MCP settings file is correct and that you've built the server with
npm run build. - API Rate Limits: The Strava API has rate limits. If you encounter rate limit errors, wait a few minutes before trying again.
License
This project is licensed under the MIT License.
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.