Coach Leo MCP Server

AI running coach powered by Strava data, science-backed training plans, and community challenges.

Remote serverstreamable-httpGo

What is the Coach Leo MCP server?

If you already use Coach Leo, the coach leo mcp server is the piece that lets your assistant work with it directly. AI running coach powered by Strava data, science-backed training plans, and community challenges.

What the server does

An AI running coach that connects to your Strava, Suunto, or Polar data, builds plans from your real history, and adapts daily based on how you actually feel.

Coach Leo is a full AI running coach application at coachleo.ai. It connects to your Strava account, reads your real training history (pace, heart rate, elevation, cadence), and uses specialized coaching tools to make decisions — like a real coach with access to your training diary.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • get_coaching_briefing — Complete coaching context: profile, recent activities, training load, alerts, readiness, character status
  • athlete — Runner profile and running character management. Body metrics, preferences, character recalculation
  • activity — Query and annotate synced activities. Filter by date, sport, impact. Record feedback
  • training — Create and manage personalized training plans. Modify sessions, track adherence
  • body_signals — Log body observations, record physical setbacks, daily readiness check-ins
  • shoes — Track shoe collection, wear inspections across 6 zones, mileage stats, and retirement
  • race — Full race lifecycle: discovery via web search, registration, preparation, results, post-race analysis
  • race_performance — Race-time estimates and VO2max across distances from training data — trail-adjusted, tracked over time
  • knowledge — Hybrid semantic + full-text search across 200+ peer-reviewed papers
  • memory — Persistent memory across sessions. Logs decisions, prevents contradictory advice
  • get_skill_workflow — Loads a predefined coaching workflow that chains tools for a complex scenario
  • Authentication — The Authentication tool exposed by this server

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Coach Leo's toolset — get_coaching_briefing, athlete, activity and 9 more — is a fair guide to whether it matches your workflow. It is maintained by leo-runningcoach; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Coach Leo.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
get_coaching_briefingComplete coaching context: profile, recent activities, training load, alerts, readiness, character status.
athleteRunner profile and running character management. Body metrics, preferences, character recalculation.
activityQuery and annotate synced activities. Filter by date, sport, impact. Record feedback.
trainingCreate and manage personalized training plans. Modify sessions, track adherence.
body_signalsLog body observations, record physical setbacks, daily readiness check-ins.
shoesTrack shoe collection, wear inspections across 6 zones, mileage stats, and retirement.
raceFull race lifecycle: discovery via web search, registration, preparation, results, post-race analysis.
race_performanceRace-time estimates and VO2max across distances from training data — trail-adjusted, tracked over time.
knowledgeHybrid semantic + full-text search across 200+ peer-reviewed papers.
memoryPersistent memory across sessions. Logs decisions, prevents contradictory advice.
get_skill_workflowLoads a predefined coaching workflow that chains tools for a complex scenario.
AuthenticationThe Authentication tool exposed by this server.

How to install the Coach Leo MCP server

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

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Coach Leo to get coaching briefing.
  • Use Coach Leo to athlete.
  • Use Coach Leo to activity.

Frequently asked questions

It connects Coach Leo to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (get_coaching_briefing, athlete, activity, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Coach Leo directly.