Model Context Protocol

TrainingPeaks MCP Server

Query training data, performance trends, CTL/ATL/TSB analysis, and training load optimization through Claude Desktop.

$ uvx tp-mcp-server
PyPI GitHub

Features

13 tools across 5 categories

Everything you need to analyze your training data — from raw workouts to computed fitness metrics and performance trends.

🔒 Auth

2 tools

  • tp_auth_status Check authentication
  • tp_refresh_auth Refresh session

👤 Profile

1 tool

  • tp_get_profile Athlete profile + auto-detect ID

🏃 Workouts

2 tools

  • tp_get_workouts List workouts by date range
  • tp_get_workout Detailed workout data

📈 Fitness

1 tool

  • tp_get_fitness CTL/ATL/TSB with computed values

🏆 Peaks

2 tools

  • tp_get_peaks Personal records by sport
  • tp_get_workout_prs Workout-level PRs

📊 Analytics

5 tools

  • tp_training_load_summary Weekly/monthly TSS & load ramp rate
  • tp_fitness_trend CTL trajectory & 7-day projection
  • tp_workout_analysis Efficiency factor & variability index
  • tp_performance_summary Sport-specific volume & consistency
  • tp_training_zones_distribution IF-based zone breakdown

Quick Start

Up and running in 3 steps

No cloning, no virtual environments. Install with a single command and connect to Claude Desktop.

1

Install uv

A fast Python package manager by Astral. Includes uvx for running packages without setup.

curl -LsSf https://astral.sh/uv/install.sh | sh
2

Get your auth cookie

Log in to trainingpeaks.com, open DevTools, and copy the Production_tpAuth cookie value.

Application tab → Cookies
→ trainingpeaks.com
→ Production_tpAuth → copy value
3

Configure Claude Desktop

Add the server to your Claude Desktop config and restart.

{
  "mcpServers": {
    "trainingpeaks": {
      "command": "/path/to/uvx",
      "args": ["tp-mcp-server"],
      "env": {
        "TP_AUTH_COOKIE": "your_cookie"
      }
    }
  }
}

Demo

See it in action

Ask Claude about your training — it queries TrainingPeaks in real time.

▶️

Screenshot or demo GIF coming soon