Интеграция Strava API с MCP SDK

@rbctmz

Basic information

About Интеграция Strava API с MCP SDK

Интеграция Strava API с Model Context Protocol SDK

Интеграция Strava API с MCP SDK config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-strava": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "."
      ]
    }
  }
}

Интеграция Strava API с MCP SDK tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Интеграция Strava API с Model Context Protocol (MCP) SDK?

This server integrates the Strava API with the Model Context Protocol (MCP) SDK, enabling AI assistants to analyze workouts and provide training recommendations based on the user’s Strava data. It is intended for athletes and developers who want to leverage Strava activity data within MCP‑compatible clients such as Claude Desktop.

How to use Интеграция Strava API с Model Context Protocol (MCP) SDK?

Clone the repository, install dependencies with uv, create a Strava API application, configure environment variables (.env), run python scripts/auth.py to obtain tokens, and then start the server with mcp dev src/server.py. Resources are accessed via URIs like strava://activities and tools such as analyze_activity(activity_id).

Key features of Интеграция Strava API с Model Context Protocol (MCP) SDK

Analyze workouts from Strava
Generate training recommendations
Automatic token refresh
Rate limiting for API requests

Use cases of Интеграция Strava API с Model Context Protocol (MCP) SDK

Retrieve a list of recent activities for review
Analyze a specific activity to get pace, effort, and metrics
Compute training load summary with distance, time, and heart rate zones
View athlete’s heart rate and power training zones
Obtain recommendations for future workouts

Frequently asked questions

What does this server do?

It connects Strava’s training data to MCP tools for analyzing activities, calculating training load, and offering recommendations.

What are the dependencies?

Python 3.10+, [Claude Desktop](https://claude.ai/desktop), a Strava account, and [uv](https://github.com/astral-sh/uv) (recommended).

How do I authenticate with Strava?

Create a Strava API application, set `STRAVA_CLIENT_ID` and `STRAVA_CLIENT_SECRET` in your `.env` file, then run `python scripts/auth.py` to obtain and store the refresh token.

What are the API rate limits?

The server enforces a limit of 100 requests per 15 minutes.

Where are tokens stored?

Tokens are stored in a local `.env` file, which should be added to `.gitignore`. For CI/CD, secrets can be set via GitHub Secrets.

Comments

More Developer Tools MCP servers

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.