Strava MCP Server
Connects Claude to the Strava API to provide direct access to fitness data, including athlete statistics, detailed activity logs, and time-series performance metrics. It enables users to analyze training progress, compare workouts, and retrieve specific segment details through natural language queries.
README
Strava MCP Server
An MCP (Model Context Protocol) server that connects Claude to the Strava API, giving Claude direct access to your training data.
Features
- Athlete Profile — Get your Strava profile info
- Athlete Stats — Lifetime and recent totals (runs, rides, swims)
- Activities — List recent activities or filter by date range
- Activity Details — Deep dive into any single activity
- Activity Streams — Time-series data: GPS, heartrate, power, cadence, altitude
- Segments — Starred segments and segment details
Setup
1. Create a Strava API Application
- Go to strava.com/settings/api
- Create an application — set the Authorization Callback Domain to
localhost - Note your Client ID and Client Secret
2. Install & Authorize
npm install
npm run setup
The setup wizard will:
- Ask for your Client ID and Client Secret
- Open your browser to authorize with Strava
- Automatically catch the callback and exchange tokens
- Write your
.envfile
3. Build
npm run build
<details> <summary>Manual setup (alternative)</summary>
Open this URL in your browser (replace CLIENT_ID):
https://www.strava.com/oauth/authorize?client_id=CLIENT_ID&response_type=code&redirect_uri=http://localhost&scope=read_all,activity:read_all
After authorizing, you'll be redirected to http://localhost?code=AUTHORIZATION_CODE. Copy the code and exchange it:
curl -s -X POST 'https://www.strava.com/oauth/token' \
-F 'client_id=CLIENT_ID' \
-F 'client_secret=CLIENT_SECRET' \
-F 'code=AUTHORIZATION_CODE' \
-F 'grant_type=authorization_code'
Save the refresh_token from the response and create a .env file:
STRAVA_CLIENT_ID=your_client_id
STRAVA_CLIENT_SECRET=your_client_secret
STRAVA_REFRESH_TOKEN=your_refresh_token
</details>
4. Configure Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"strava": {
"command": "node",
"args": ["/Users/USERNAME/Apps/StravaMCP/dist/index.js"],
"env": {
"STRAVA_CLIENT_ID": "your_client_id",
"STRAVA_CLIENT_SECRET": "your_client_secret",
"STRAVA_REFRESH_TOKEN": "your_refresh_token"
}
}
}
}
Restart Claude Desktop. You should see the Strava tools available in the tools menu (hammer icon).
Available Tools
| Tool | Description |
|---|---|
get_athlete |
Get your Strava profile |
get_athlete_stats |
Get lifetime and recent statistics |
get_activities |
List recent activities (paginated) |
get_activities_between |
Get all activities within a date range (auto-paginated) |
get_activity |
Get detailed info for one activity |
get_activity_laps |
Get lap/split data for an activity |
get_activity_zones |
Get HR and power zone distribution |
get_activity_streams |
Get time-series data (GPS, HR, power, etc.) |
get_starred_segments |
Get your starred segments |
get_segment |
Get details for a specific segment |
get_segment_efforts |
Get your efforts on a segment (with optional date filter) |
Example Prompts
Once connected, try asking Claude:
- "What were my activities this week?"
- "Analyze my running performance over the past month"
- "Compare my cycling times in January vs February"
- "Show me my heartrate data from my last run"
- "What are my all-time stats?"
Development
# Run in dev mode (no build step)
npm run dev
# Build for production
npm run build
npm start
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.