Leo - Running Coach

Name: Leo - Running Coach
Author: leo-runningcoach

@leo-runningcoach

About Leo - Running Coach

AI running coach that syncs your Strava data, builds personalized training plans, manages your race calendar, tracks body signals and shoes, and assigns you a running character. Join pack challenges and collective expeditions with your community. Backed by 70+ sports science pape

#running #strava #coaching #training #trail #fitness #sports #health

Basic information

Config

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

{
  "mcpServers": {
    "coach-leo": {
      "url": "https://mcp.coachleo.ai/mcp"
    }
  }
}

Tools

No tools detected

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

Overview

What is Leo - Running Coach?

Leo - Running Coach is an AI running coach MCP server that connects to your Strava account, builds training plans from your real data, and adapts daily based on how you actually feel. It uses 12 specialized coaching tools and draws from 65+ peer-reviewed sports science papers. It is intended for runners who want a personalized, data-driven coaching experience.

How to use Leo - Running Coach?

Create an account at coachleo.ai (7-day free trial), connect your Strava account (read-only), then add the remote MCP server URL https://mcp.coachleo.ai/mcp to any MCP-compatible client (ChatGPT, Claude Desktop, etc.) and authenticate with your Coach Leo account. No local installation is required.

Key features of Leo - Running Coach

Strava-first coaching with 30-minute sync intervals
Training plans built from your actual 8-week pace data
Multi-indicator overtraining prevention using five metrics
Biomechanical shoe wear analysis across six zones
Web-search-based race preparation with GPX profile analysis
Persistent coaching memory across all conversations

Use cases of Leo - Running Coach

Create and adapt a personalized training plan for an upcoming race
Monitor daily readiness and receive real-time workout adjustments
Analyze running form and shoe wear patterns for injury prevention
Get evidence-based race fueling and recovery nutrition guidance
Track long-term fitness trends with VO2max and race time predictions

FAQ from Leo - Running Coach

How is this different from generic chatbot running plans?

Leo does not generate plans from what you type; it deduces your training patterns from your Strava data, derives actual paces from 8 weeks of history, and adapts your plan daily through conversation.

What data does Leo - Running Coach access and where is it stored?

Leo connects to Strava with read-only permission, hosted in Finland (Hetzner, EU) with HTTPS/TLS encryption, GDPR compliance, and strict user data isolation. No data is used for AI model training.

What runtime or dependencies are required to use the MCP server?

No installation is needed — Leo is a hosted remote MCP server. You only need a Coach Leo account and an MCP-compatible client (ChatGPT, Claude Desktop, Cursor, Windsurf, etc.).

How does Leo - Running Coach authenticate?

It implements full OAuth 2.1 with PKCE (S256), Dynamic Client Registration, token refresh and revocation, and a discovery endpoint at /.well-known/oauth-authorization-server.

Does Leo - Running Coach have usage limits or pricing?

A 7-day free trial is available. After that, it costs $9.99/month for founding members or $12.99/month regularly. All features are included with no tiers or feature gates.

Comments

More Other MCP servers

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K