strava-mcp-agent

Give Claude access to your Strava data. An MCP server that exposes your runs, rides, swims, and all Strava metrics as tools for AI-powered coaching, analysis, and conversation.

What it does

strava-mcp-agent connects your Strava account to any MCP-compatible client (Claude Desktop, Claude Code, etc.) and provides 13 tools covering every aspect of your athletic data:

Quick Start

Step 1: Install

pip install strava-mcp-agent

Step 2: Create a Strava API app (one time)

Go to strava.com/settings/api and fill in:

The callback domain must be localhost — this is what allows the setup wizard to receive the authorization code on your machine.

Click Create. On the next page, copy your Client ID (a number like 123456) and Client Secret (a long code like abc123def456...).

Step 3: Run the setup wizard

strava-mcp-token

It will:

1. Ask for your Client ID and Client Secret
2. Open your browser — click Authorize on the Strava page
3. Auto-detect your OS (macOS / Linux / Windows)
4. Find the Python that has the package installed
5. Write the Claude Desktop config file for you

Step 4: Restart Claude Desktop

That's it. Your 13 Strava tools are ready. Just ask Claude about your runs.

Manual setup (if you prefer)

{
  "mcpServers": {
    "strava": {
      "command": "strava-mcp",
      "env": {
        "STRAVA_CLIENT_ID": "your_client_id",
        "STRAVA_CLIENT_SECRET": "your_client_secret",
        "STRAVA_REFRESH_TOKEN": "your_refresh_token"
      }
    }
  }
}

Usage Examples

Once connected, just talk to Claude:

• "How was my running this month?"
• "Compare my last 5 runs — am I getting faster?"
• "What's my average heart rate on long runs vs tempo runs?"
• "Show me my weekly mileage trend for the past 2 months"
• "What gear has the most miles on it?"

The get_running_summary tool is especially powerful for coaching — it computes weekly mileage, pace trends, best 5K/10K efforts, and heart rate stats, all in one call.

Security

Credentials are loaded from environment variables only — never hardcoded. The server uses Strava's OAuth2 refresh token flow and automatically handles token renewal.

Requirements

• Python 3.10+
• A Strava account with API access
• MCP-compatible client (Claude Desktop, Claude Code, etc.)

License

MIT