mcpField
S
Strava MCP Server

Strava MCP Server

Local
github.com/tomekkorbakHealth25Updated 73w ago

About Strava MCP Server

Strava MCP Server is an MCP server that gives language models access to athlete activity data from the Strava API. It exposes tools for listing recent activities, querying date ranges and fetching single activity details. Returned fields use consistent metric units.

Key features

  1. 01List recent activities with a limit
  2. 02Query activities within a date range
  3. 03Filter activities from the past number of days
  4. 04Fetch detailed data for a single activity by ID
  5. 05Return distance, time, speed and elevation in metric units

Use cases

  1. 01Review training from the previous week
  2. 02Find the longest run in the past month
  3. 03Get details of the latest cycling activity

MCP support

This project is an MCP server that exposes tools for querying Strava activities to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Strava MCP Server

Python Package License: MIT Python 3.10 Install MCP Server

A Model Context Protocol (MCP) server that provides access to the Strava API. It allows language models to query athlete activities data from the Strava API.

Available Tools

The server exposes the following tools:

Activities Queries
  • get_activities(limit: int = 10): Get the authenticated athlete's recent activities
  • get_activities_by_date_range(start_date: str, end_date: str, limit: int = 30): Get activities within a specific date range
  • get_activity_by_id(activity_id: int): Get detailed information about a specific activity
  • get_recent_activities(days: int = 7, limit: int = 10): Get activities from the past X days

Dates should be provided in ISO format (YYYY-MM-DD).

Activity Data Format

The server returns activity data with consistent field names and units:

FieldDescriptionUnit
nameActivity name-
sport_typeType of sport-
start_dateStart date and timeISO 8601
distance_metresDistancemeters
elapsed_time_secondsTotal elapsed timeseconds
moving_time_secondsMoving timeseconds
average_speed_mpsAverage speedmeters per second
max_speed_mpsMaximum speedmeters per second
total_elevation_gain_metresTotal elevation gainmeters
elev_high_metresHighest elevationmeters
elev_low_metresLowest elevationmeters
caloriesCalories burnedkcal
start_latlngStart coordinates[lat, lng]
end_latlngEnd coordinates[lat, lng]

Authentication

To use this server, you'll need to authenticate with the Strava API. Follow these steps:

  1. Create a Strava API application:

    • Go to Strava API Settings
    • Create an application to get your Client ID and Client Secret
    • Set the Authorization Callback Domain to localhost
  2. Get your refresh token:

    • Use the included get_strava_token.py script:
    python get_strava_token.py
    
    • Follow the prompts to authorize your application
    • The script will save your tokens to a .env file
  3. Set environment variables: The server requires the following environment variables:

    • STRAVA_CLIENT_ID: Your Strava API Client ID
    • STRAVA_CLIENT_SECRET: Your Strava API Client Secret
    • STRAVA_REFRESH_TOKEN: Your Strava API Refresh Token

Usage

Claude for Desktop

Update your claude_desktop_config.json (located in ~/Library/Application\ Support/Claude/claude_desktop_config.json on macOS and %APPDATA%/Claude/claude_desktop_config.json on Windows) to include the following:

{
    "mcpServers": {
        "strava": {
            "command": "uvx",
            "args": [
                "strava-mcp-server"
            ],
            "env": {
                "STRAVA_CLIENT_ID": "YOUR_CLIENT_ID",
                "STRAVA_CLIENT_SECRET": "YOUR_CLIENT_SECRET",
                "STRAVA_REFRESH_TOKEN": "YOUR_REFRESH_TOKEN"
            }
        }
    }
}
Claude Web

For Claude Web, you can run the server locally and connect it using the MCP extension.

Example Queries

Once connected, you can ask Claude questions like:

  • "What are my recent activities?"
  • "Show me my activities from last week"
  • "What was my longest run in the past month?"
  • "Get details about my latest cycling activity"

Error Handling

The server provides human-readable error messages for common issues:

  • Invalid date formats
  • API authentication errors
  • Network connectivity problems

License

This project is licensed under the MIT License - see the LICENSE file for details.

Comments

Markdown supported

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.