1
Quick Start
Matthias Hinrichs edited this page 2026-05-14 19:43:42 +00:00
This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Quick Start

Get the Strava MCP Server running in under 2 minutes — no repository clone required.

Step 1: Authenticate

Run the interactive setup wizard. It will open a browser window, guide you through creating a Strava API app, and save your credentials automatically.

uvx --from strava-mcp-server-hnrx auth

The wizard will:

  1. Open http://localhost:8765 in your browser
  2. Show you how to create a Strava API application
  3. Accept your Client ID and Client Secret
  4. Redirect you to Strava for OAuth authorization
  5. Save all credentials to ~/.config/strava-mcp-server/config.env

You only need to run auth once. The credentials are stored permanently in your user config directory.

Step 2: Run the Server

uvx --from strava-mcp-server-hnrx server

The server starts in STDIO mode by default — perfect for use with Claude Desktop, Cursor, or the MCP Inspector.

For HTTP mode (e.g. for Docker or OpenWebUI):

MCP_TRANSPORT=http uvx --from strava-mcp-server-hnrx server

Step 3: Connect your AI Client

→ See MCP Clients for Claude Desktop, OpenWebUI, and other client configurations.


What happens next?

Once connected, your AI assistant can:

  • Analyze your training load and weekly volume
  • Compare activities across seasons
  • Identify your best segments and performances
  • Track gear mileage and recommend maintenance
  • Generate structured training reports

Back to Home