TrainingPeaks MCP Server

Connect TrainingPeaks to Claude and other AI assistants via the Model Context Protocol (MCP). Query your workouts, analyze training load, compare power data, and track fitness trends through natural conversation.

No API approval required. The official Training Peaks API is approval-gated, but this server uses secure cookie authentication that any user can set up in minutes. Your cookie is stored in your system keyring, never transmitted anywhere except to TrainingPeaks.

What You Can Do

Ask your AI assistant questions like:

• "Compare my FTP progression this year vs last year"

• "What was my TSS ramp rate in the 6 weeks before my best 20-min power?"

• "Am I ready to race? Show my form trend and recent workout quality"

• "Which days of the week do I typically train hardest?"

• "Find weeks where I exceeded 800 TSS and show what happened to my form after"

Features

Setup Options

Option A: Auto-Setup with Claude Code

If you have Claude Code, paste this prompt:

Claude will handle the installation and guide you through authentication step-by-step.

Option B: Manual Setup

Step 1: Install

Step 2: Authenticate

Option A: Auto-extract from browser (easiest)

If you're logged into TrainingPeaks in your browser:

macOS note: You may see security prompts for Keychain or Full Disk Access. This is normal - browser cookies are encrypted and require permission to read.

Option B: Manual cookie entry

1. Log into app.trainingpeaks.com

2. Open DevTools (F12) → Application tab → Cookies

3. Find Production_tpAuth and copy its value

4. Run tp-mcp auth and paste when prompted

Other auth commands:

Step 4: Add to Claude Desktop

Run this to get your config snippet:

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and paste it inside mcpServers. Example with multiple servers:

Restart Claude Desktop. You're ready to go!

Tool Reference

tp_get_workouts

List workouts in a date range. Max 90 days per query.

tp_get_workout

Get full details for one workout including power, HR, cadence, TSS.

tp_get_peaks

Get ranked personal records. Bike: power metrics. Run: pace/speed metrics.

Bike types: power5sec, power1min, power5min, power10min, power20min, power60min, power90min

Run types: speed400Meter, speed1K, speed5K, speed10K, speedHalfMarathon, speedMarathon

tp_get_fitness

Get training load metrics over time.

Returns daily CTL (chronic training load / fitness), ATL (acute training load / fatigue), and TSB (training stress balance / form).

tp_get_workout_prs

Get PRs set during a specific workout.

What is MCP?

Model Context Protocol is an open standard for connecting AI assistants to external data sources. MCP servers expose tools that AI models can call to fetch real-time data, enabling assistants like Claude to access your Training Peaks account through natural language.

Security

TL;DR: Your cookie is encrypted on disk, exchanged for short-lived OAuth tokens, never shown to Claude, and only ever sent to TrainingPeaks. The server is read-only and has no network ports.

This server is designed with defense-in-depth. Your TrainingPeaks session cookie is sensitive - it grants access to your training data - so we treat it accordingly.

Cookie Storage

Your cookie is never stored in plaintext. The encrypted file fallback uses Fernet symmetric encryption with a machine-specific key.

Cookie Never Leaks to AI

The AI assistant (Claude) never sees your cookie value. Multiple layers ensure this:

1. Return value sanitization: Tool results are scrubbed for any keys containing cookie, token, auth, credential, password, or secret before being sent to Claude

2. Masked repr(): The BrowserCookieResult class overrides __repr__ to show cookie=<present> instead of the actual value

3. Sanitized exceptions: Error messages use only exception type names, never full messages that could contain data

4. No logging: Cookie values are never written to any log

Domain Hardcoding (Cannot Be Changed)

The browser cookie extraction only accesses .trainingpeaks.com:

Claude cannot modify this via tool parameters. The only parameter is browser (chrome/firefox/etc), not the domain. To change the domain would require modifying the source code.

Read-Only Access

This server provides read-only access to TrainingPeaks:

• ✅ Query workouts, fitness metrics, personal records

• ❌ Cannot create, modify, or delete workouts

• ❌ Cannot change account settings

• ❌ Cannot access billing or payment info

No Network Exposure

The MCP server uses stdio transport only - it communicates with Claude Desktop via stdin/stdout, not over the network. There is no HTTP server, no open ports, no remote access.

What This Server Cannot Do

Open Source

This server is fully open source. You can audit every line of code before running it. Key security files:

• src/tp_mcp/auth/browser.py - Cookie extraction with hardcoded domain

• src/tp_mcp/tools/refresh_auth.py - Result sanitization

• tests/test_tools/test_refresh_auth_security.py - Security tests

Authentication Flow

The server uses a two-step authentication process:

1. Cookie → OAuth Token: Your stored cookie is exchanged for a short-lived OAuth access token (expires in 1 hour)

2. Automatic Refresh: Tokens are cached in memory and automatically refreshed before expiry

This means:

• You only need to authenticate once with tp-mcp auth

• API calls use proper Bearer token auth, not cookies

• If your session cookie expires (typically after several weeks), use tp_refresh_auth in Claude or run tp-mcp auth again

Development

License

MIT