Strava
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 speci
What is Strava?
Strava is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 train...
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 speci
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- get-athlete-profile
- get-athlete-stats
- get-activity-details
- get-recent-activities
- list-athlete-clubs
Use Cases
Maintainer
Works with
Installation
NPM
npx -y strava-mcp-serverManual Installation
npx -y strava-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Strava
The Strava MCP Server connects Claude and other AI assistants directly to the Strava API, exposing 25 tools that retrieve athlete profiles, activity logs, segment data, club memberships, routes, and time-series performance metrics including heart rate, power, and cadence. Athletes and coaches use it to ask conversational questions about training history, compare workouts, discover segments, and export routes as GPX or TCX files — all without leaving their AI chat interface. Authentication is handled through Strava's OAuth flow with credentials stored securely in environment variables or a local config file.
Prerequisites
- Node.js installed (for npx execution)
- A Strava account with activities recorded
- A Strava API application created at https://www.strava.com/settings/api to obtain Client ID and Client Secret
- Strava OAuth tokens (access token and refresh token) obtained through the OAuth flow
- Claude Desktop or another MCP-compatible AI client
Create a Strava API application
Go to https://www.strava.com/settings/api and create a new application. Note the Client ID and Client Secret — you will need these to generate OAuth tokens. Set the Authorization Callback Domain to localhost for local use.
Obtain OAuth access and refresh tokens
Use the Strava OAuth flow to generate an access token and refresh token. You can use the Strava API documentation's authorization flow or a tool like the Strava API OAuth helper. The access token expires; the refresh token is used to renew it automatically.
# Example OAuth authorization URL (replace CLIENT_ID):
https://www.strava.com/oauth/authorize?client_id=YOUR_CLIENT_ID&response_type=code&redirect_uri=http://localhost&scope=read,activity:read_all,profile:read_allConfigure your MCP client with Strava credentials
Add the strava-mcp-server to your Claude Desktop config with your Strava credentials as environment variables. The server reads STRAVA_CLIENT_ID, STRAVA_CLIENT_SECRET, STRAVA_ACCESS_TOKEN, and STRAVA_REFRESH_TOKEN.
{
"mcpServers": {
"strava": {
"command": "npx",
"args": ["-y", "strava-mcp-server"],
"env": {
"STRAVA_CLIENT_ID": "your_client_id",
"STRAVA_CLIENT_SECRET": "your_client_secret",
"STRAVA_ACCESS_TOKEN": "your_access_token",
"STRAVA_REFRESH_TOKEN": "your_refresh_token"
}
}
}
}Optionally configure route export path
Set the ROUTE_EXPORT_PATH environment variable to specify a directory where GPX and TCX route files will be saved when you request route exports.
"ROUTE_EXPORT_PATH": "/Users/yourname/Downloads/strava-routes"Restart Claude Desktop and start querying your fitness data
Restart Claude Desktop after saving the config. The server exposes 25 tools covering activities, stats, segments, routes, clubs, and workouts. Ask Claude about your training data in natural language.
Strava Examples
Client configuration
Configure Claude Desktop with the strava-mcp-server npm package and your Strava API credentials.
{
"mcpServers": {
"strava": {
"command": "npx",
"args": ["-y", "strava-mcp-server"],
"env": {
"STRAVA_CLIENT_ID": "12345",
"STRAVA_CLIENT_SECRET": "your_client_secret",
"STRAVA_ACCESS_TOKEN": "your_access_token",
"STRAVA_REFRESH_TOKEN": "your_refresh_token",
"ROUTE_EXPORT_PATH": "/Users/yourname/Downloads/routes"
}
}
}
}Prompts to try
With your Strava account connected, try these natural language prompts to analyze your fitness data.
- "How many kilometers did I run this month compared to last month?"
- "Analyze my last cycling ride — show me average power, heart rate, and cadence"
- "What are my top 5 fastest 5K segments ever?"
- "List my starred segments and find any near San Francisco"
- "Export my longest route this year as a GPX file"Troubleshooting Strava
Authentication error: access token expired or invalid
Strava access tokens expire after 6 hours. The server uses STRAVA_REFRESH_TOKEN to automatically renew them. If the refresh token is also invalid (they expire after extended inactivity), redo the OAuth authorization flow to generate fresh tokens and update your config.
No activities returned even though activities exist on Strava
The OAuth scope must include `activity:read_all` to access private activities. Re-authorize with the full scope: `scope=read,activity:read_all,profile:read_all`. Check that STRAVA_CLIENT_ID and STRAVA_CLIENT_SECRET are correct for the application that issued the tokens.
GPX/TCX export fails or file not found after export
Ensure ROUTE_EXPORT_PATH points to an existing directory that the process has write permission to. If the variable is not set, check the default export location. Create the directory manually if it does not exist.
Frequently Asked Questions about Strava
What is Strava?
Strava is a Model Context Protocol (MCP) server that 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 speci It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Strava?
Install via npm with the command: npx -y strava-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Strava?
Strava works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Strava free to use?
Yes, Strava is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Strava Alternatives — Similar Analytics Servers
Looking for alternatives to Strava? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Strava in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Strava?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.