Strava MCP Server

Strava MCP Server

Connects Claude or any MCP client to the Strava API v3, enabling access to fitness data such as activities, athletes, clubs, segments, routes, and streams.

Category
Visit Server

README

Strava MCP Server

A Model Context Protocol (MCP) server that provides full access to the Strava API v3. Connect Claude (or any MCP client) to your Strava fitness data — activities, athletes, clubs, segments, routes, streams, gear, and more.

Features

  • 30+ tools covering all major Strava API v3 endpoints
  • Auto token refresh — OAuth2 tokens are refreshed and cached automatically
  • Formatted responses — distances in km, times in minutes, speeds in km/h
  • Convenience tools — weekly/monthly summaries, filter by sport type

Available Tools

Category Tools
Activities Create, get details, comments, kudos, laps, list, zones, update
Athletes Profile, zones, stats, update weight
Clubs List, details, members, admins, activities
Gear Get gear details (bikes & shoes)
Routes List, details, GPX export, TCX export
Segments Explore, starred, details, star/unstar
Segment Efforts List efforts, effort details
Streams Activity, route, effort, segment time-series data
Uploads Upload status
Summaries Weekly summary, monthly summary, filter by sport type, filter by date

Prerequisites

  • Python 3.12+
  • uv (Python package manager)
  • A Strava account
  • A Strava API application (see setup below)

Setup

1. Create a Strava API Application

  1. Go to https://www.strava.com/settings/api
  2. Create a new application:
    • Application Name: anything (e.g. "MCP Server")
    • Category: choose any
    • Website: http://localhost
    • Authorization Callback Domain: localhost
  3. Note your Client ID and Client Secret

2. Clone and Install

git clone https://github.com/manojanasuri16/strava-mcp-server.git
cd strava-mcp-server
uv sync

3. Configure Environment

Create a .env file in the project root:

STRAVA_CLIENT_ID=<your_client_id>
STRAVA_CLIENT_SECRET=<your_client_secret>
STRAVA_REFRESH_TOKEN=<your_refresh_token>

To get your refresh token, follow the OAuth Authorization steps below.

4. OAuth Authorization (Getting Your Refresh Token)

Strava uses OAuth2. You need to authorize the app once to get a refresh token.

Step 1: Authorize in browser

Open this URL in your browser (replace YOUR_CLIENT_ID):

https://www.strava.com/oauth/authorize?client_id=YOUR_CLIENT_ID&response_type=code&redirect_uri=http://localhost&scope=read_all,activity:read_all,activity:write,profile:read_all,profile:write

Step 2: Grab the authorization code

After you click "Authorize", Strava redirects to:

http://localhost?code=AUTHORIZATION_CODE&scope=...

Copy the code value from the URL. This code is single-use and expires in minutes, so proceed quickly.

Step 3: Exchange code for tokens

On Linux/macOS (bash):

curl -X POST https://www.strava.com/api/v3/oauth/token \
  -d client_id=YOUR_CLIENT_ID \
  -d client_secret=YOUR_CLIENT_SECRET \
  -d code=AUTHORIZATION_CODE \
  -d grant_type=authorization_code

On Windows (PowerShell):

Invoke-RestMethod -Method Post -Uri "https://www.strava.com/api/v3/oauth/token" -Body @{
  client_id = "YOUR_CLIENT_ID"
  client_secret = "YOUR_CLIENT_SECRET"
  code = "AUTHORIZATION_CODE"
  grant_type = "authorization_code"
}

Step 4: Save the refresh token

The response will include access_token, refresh_token, and expires_at. Copy the refresh_token value into your .env file.

The server will automatically refresh the access token when it expires using this refresh token.

Usage

Test with MCP Inspector

The MCP Inspector provides a web UI to test your tools:

uv run mcp dev strava_server.py
  1. Open the Inspector URL shown in the terminal
  2. Click Connect
  3. Go to the Tools tab
  4. Try running a tool like get_athlete_profile or get_recent_activities

Use with Claude Code (CLI)

From your project directory, register the server:

claude mcp add strava -- uv run strava_server.py

Then start a new Claude Code session and ask things like:

  • "How was my running this week?"
  • "Show me my last 10 activities"
  • "What are my all-time cycling stats?"
  • "Find popular running segments near Bangalore"
  • "Create a manual yoga activity for today"

Use with Claude Desktop

uv run mcp install strava_server.py

Or manually add to your config file:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "strava": {
      "command": "uv",
      "args": ["run", "strava_server.py"],
      "cwd": "/path/to/strava-mcp-server"
    }
  }
}

Restart Claude Desktop after saving.

Use with ChatGPT Desktop

  1. Open ChatGPT Desktop app
  2. Go to Settings > MCP
  3. Add a new server with:
    • Name: strava
    • Command: uv run strava_server.py
    • Working directory: /path/to/strava-mcp-server

Restart ChatGPT Desktop after adding.

Use with Cursor / VS Code

Add to .cursor/mcp.json or .vscode/mcp.json in your workspace:

{
  "servers": {
    "strava": {
      "command": "uv",
      "args": ["run", "strava_server.py"],
      "cwd": "/path/to/strava-mcp-server"
    }
  }
}

Run Standalone

uv run strava_server.py

Troubleshooting

401 Unauthorized Error

This is the most common issue. It means your access token is invalid.

Cause 1: Stale cached tokens

The server caches tokens at ~/.strava-mcp-tokens.json. If this file contains expired/invalid tokens, the server will keep using them.

Fix:

# Linux/macOS
rm ~/.strava-mcp-tokens.json

# Windows (PowerShell)
Remove-Item "$HOME\.strava-mcp-tokens.json" -ErrorAction SilentlyContinue

Then restart the server.

Cause 2: Invalid refresh token

Your refresh token in .env may be expired or revoked. This happens if:

  • You re-authorized the app and got a new refresh token (old one is invalidated)
  • You revoked the app's access in Strava settings
  • The token was never obtained properly

Fix: Redo the OAuth Authorization steps to get a fresh refresh token.

Cause 3: Wrong client credentials

Double-check your STRAVA_CLIENT_ID and STRAVA_CLIENT_SECRET in .env match what's shown at https://www.strava.com/settings/api.

429 Rate Limit

Strava limits API requests to:

  • 100 requests per 15 minutes
  • 1,000 requests per day

The server returns a helpful error message when rate-limited. Wait a few minutes and try again.

Token Refresh Fails on Startup

If the server crashes immediately with a token error, make sure:

  1. Your .env file exists in the project root
  2. All three variables are set (STRAVA_CLIENT_ID, STRAVA_CLIENT_SECRET, STRAVA_REFRESH_TOKEN)
  3. There are no extra spaces or quotes around the values

Missing Scopes

Some tools require specific OAuth scopes:

  • activity:read_all — needed for activity details, streams
  • activity:write — needed for creating/updating activities
  • profile:read_all — needed for athlete zones
  • profile:write — needed for updating weight

If a tool returns a 403 Forbidden error, you may need to re-authorize with the correct scopes. Use the authorization URL in Step 1 above (it includes all scopes).

Project Structure

strava-mcp-server/
├── strava_server.py              # Entry point (thin wrapper)
├── src/
│   └── strava_mcp/
│       ├── __init__.py           # Package exports
│       ├── server.py             # FastMCP instance & logging
│       ├── auth.py               # OAuth2 token management
│       ├── client.py             # HTTP helpers (GET, POST, PUT)
│       ├── formatters.py         # Response formatting utilities
│       └── tools/
│           ├── __init__.py       # Auto-imports all tool modules
│           ├── activities.py     # Activity CRUD, laps, zones, comments, kudos
│           ├── athletes.py       # Profile, stats, zones, weight
│           ├── clubs.py          # Clubs, members, admins, activities
│           ├── gear.py           # Bike & shoe details
│           ├── routes.py         # Routes, GPX/TCX export
│           ├── segments.py       # Segments, efforts, explore, star
│           ├── streams.py        # Time-series data streams
│           └── extras.py         # Summaries, filters, upload status
├── pyproject.toml                # Project config and dependencies
├── uv.lock                       # Locked dependencies
├── .env                           # Your Strava credentials (not committed)
└── README.md                      # This file

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

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.

Official
Featured