About Strava MCP
Strava MCP connects Strava activity data to Claude Desktop so users can ask about their activities in conversation. It uses credentials from a Strava developer app to establish the connection.
Key features
- 01Query Strava activity information
- 02Use through Claude Desktop
- 03Connect with Strava API credentials
Use cases
- 01Ask about the latest activity
- 02Review personal activity records conversationally
MCP support
The MCP server connects to Strava and lets Claude Desktop query the user's activity information.
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
This repository contains a Strava MCP which you can add to your Claude Desktop client. Once installed, you'll be able to ask Claude all about your activities!
Checkout my blog post here
Setup
Dependencies
- Claude Desktop
uv- A Stava account with a develop app setup
Connecting to Strava
Once you have an app setup on your Strava profile and you've cloned this repository, create an .env file at the root with the following contents:
STRAVA_CLIENT_ID=<fill-me-in>
STRAVA_CLIENT_SECRET=<fill-me-in>
STRAVA_ACCESS_TOKEN=<fill-me-in>
STRAVA_REFRESH_TOKEN=<fill-me-in>
Connecting the MCP to Claude
You can add the server to your Claude config by running the following:
uv run mcp install main.py
If you make changes to the server, you will need to restart your Claude desktop client.
Once installed, you should see a hammer icon at the bottom of the text box on your Claude app. If you click on it, it should show the following:

Running
Now the server is added, Claude should be able to use it.
Try: "tell me about my latest activity".

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.