TrainingPeaks MCP Server

Connect Training
Data to AI

14 tools for training load analysis, fitness trends, workout breakdowns, and performance optimization — right inside Claude Desktop.

What You Can Do

From daily workouts to long-term performance trends.

🔒

Secure Connection

Paste your cookie once. Automatic token management handles the rest.

🏃

Athlete Identity

Auto-detects your athlete ID and profile. Your AI knows who it's coaching.

🏋

Workouts & Plans

Past sessions, detailed breakdowns, and upcoming planned workouts with coach instructions.

💓

Fitness & Freshness

Track your CTL, ATL, and TSB over time. Values are computed from TSS using standard exponential moving averages.

🏆

Personal Records

Best efforts across every sport and duration — power peaks, pace PRs, and workout-specific bests.

📊

Deep Analytics

Training load ramp rates, fitness projections, efficiency factors, zone distribution, and sport-specific performance summaries.

Quick Start

Up and running in 3 steps. No cloning, no virtual environments.

01

Install uv

Install the fast Python package manager. It includes uvx for running packages without setup.

curl -LsSf https://astral.sh/uv/install.sh | sh
02

Get Auth Cookie

Log in to trainingpeaks.com, open DevTools, go to Application → Cookies, and copy the Production_tpAuth value.

03

Add to Claude

Add to your Claude Desktop config and restart.

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

Try Asking

Connect your Port, then ask.

"What's my current fitness level?"
📅 "Show my planned workouts for the next 2 weeks"
📈 "Show my training load trend for the last 3 months"
🚲 "Analyze my last bike workout"
🏆 "What are my power PRs?"
📊 "How is my training zone distribution this month?"