MCP Catalogs
Hometrainingpeaks-mcp screenshot

trainingpeaks-mcp

by JamsusMaximus·65·Score 48

TrainingPeaks MCP server enables querying workouts, fitness data, and PRs via natural language.

developer-toolsproductivityhealth
33
Forks
15
Open issues
this month
Last commit
2d ago
Indexed

Overview

This MCP server connects TrainingPeaks to Claude Desktop, Code and Cowork via the Model Context Protocol. It provides 62 tools for managing workouts, analyzing fitness data, tracking PRs, and updating athlete settings. The server uses secure cookie authentication that works with any TrainingPeaks account without requiring API approval. Your credentials are stored in your system keyring and never transmitted except to TrainingPeaks. The server is actively maintained with recent commits and includes comprehensive documentation.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

you:Build structured training workouts with intervals and automatically calculated IF/TSS
you:Compare FTP progression and fitness metrics (CTL/ATL/TSB) between different periods
you:Schedule workouts and manage training calendar with natural language commands
you:Log health metrics and track progress over time
you:Do I need API approval to use this server?
you:How are my credentials stored?

When to choose this

Choose this server if you use TrainingPeaks for fitness tracking and want AI assistance for planning and analyzing your training without going through the API approval process.

When NOT to choose this

Don't choose this if you use a different fitness platform or need official API integration with advanced features not supported by cookie-based authentication.

Tools this server exposes

12 tools extracted from the README
  • tp_get_workouts

    List workouts in a date range (max 90 days)

  • tp_get_workout

    Get full details for a single workout

  • tp_create_workout

    Create a workout with optional interval structure

  • tp_analyze_workout

    Detailed analysis with time-series data, zones, and laps

  • tp_get_fitness

    Get CTL, ATL, and TSB trend (fitness, fatigue, form)

  • tp_get_peaks

    Power PRs (5s-90min) and running PRs (400m-marathon)

  • tp_update_ftp

    Update FTP and recalculate the default power zones

  • tp_log_metrics

    Log weight, HRV, sleep, steps, SpO2, pulse, RMR, injury

  • tp_get_events

    List events in a date range

  • tp_create_event

    Add a race/event with priority and CTL target

  • tp_get_profile

    Get athlete profile

  • tp_auth_status

    Check authentication status

Comparable tools

strava-mcpgarmin-mcpfitness-api-mcpworkout-planning-ai

Installation

Option A: Auto-Setup with Claude Code

If you have [Claude Code](https://claude.ai/code), paste this prompt:

Set up the TrainingPeaks MCP server from https://github.com/JamsusMaximus/trainingpeaks-mcp - clone it, create a venv, install it, then walk me through getting my TrainingPeaks cookie from my browser and run tp-mcp auth. Finally, add it to my Claude Desktop config.

Option B: Manual Setup

Step 1: Install
git clone https://github.com/JamsusMaximus/trainingpeaks-mcp.git
cd trainingpeaks-mcp
python3 -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
pip install -e .
Step 2: Authenticate
pip install tp-mcp[browser]  # One-time: install browser support
tp-mcp auth --from-browser chrome  # Or: firefox, safari, edge, auto
Step 3: Add to Claude Desktop

Run this to get your config snippet:

tp-mcp config

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

FAQ

Do I need API approval to use this server?
No. This server uses secure cookie authentication that works with any TrainingPeaks account, bypassing the API approval requirement.
How are my credentials stored?
Your cookie is encrypted and stored in your system keyring, never transmitted anywhere except to TrainingPeaks itself.

Compare trainingpeaks-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.