TrainingPeaks

v1.0.0Analyticsstable

TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.

claudeclaude-desktopcyclingfitnessmcp
Share:
71
Stars
0
Downloads
0
Weekly
0/5

What is TrainingPeaks?

TrainingPeaks is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to trainingpeaks mcp server for claude desktop, code and cowork. no api approval needed - works with any account. query workouts, ctl/atl/tsb fitness data, power prs via natural language.

TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • TrainingPeaks MCP server for Claude Desktop, Code and Cowork

Use Cases

Query workout history and fitness data naturally.
Analyze CTL/ATL/TSB metrics and power PRs.
Track cycling and running performance without API approval.
JamsusMaximus

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx trainingpeaks-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use TrainingPeaks

The TrainingPeaks MCP server connects Claude Desktop and other MCP clients to your TrainingPeaks account, exposing 64 tools that cover the full spectrum of endurance athlete data — workout creation, retrieval, and editing; CTL/ATL/TSB fitness trend analysis; power and running PRs; weekly summaries; athlete settings (FTP, heart rate zones); health metrics logging (weight, HRV, sleep, SpO2); equipment management; and calendar planning. Crucially, it works with any TrainingPeaks account without requiring official API approval, authenticating via your existing browser session cookies. Cyclists, runners, and coaches can ask Claude to analyze training load, log workouts, plan race blocks, or set training zones entirely through natural language.

Prerequisites

  • Python 3.10+ installed with pip or uv available
  • A TrainingPeaks account (free or premium — no API approval required)
  • Google Chrome, Firefox, or Edge browser with an active TrainingPeaks login session (for cookie-based auth)
  • Git to clone the repository: https://github.com/JamsusMaximus/trainingpeaks-mcp
  • An MCP-compatible client such as Claude Desktop
1

Clone and install the server

Clone the repository and install it in a Python virtual environment.

git clone https://github.com/JamsusMaximus/trainingpeaks-mcp.git
cd trainingpeaks-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
2

Authenticate with your TrainingPeaks session

Run the auth command to extract your TrainingPeaks session cookies from Chrome (or another browser). This stores credentials in your platform's native secret store — no plaintext files.

source .venv/bin/activate
tp-mcp auth --from-browser chrome
# Or for manual cookie paste:
tp-mcp auth
3

Generate the Claude Desktop config snippet

Run the built-in config generator to produce the correct JSON snippet for your machine, then copy it into your claude_desktop_config.json.

source .venv/bin/activate
tp-mcp config
4

Add the config to Claude Desktop

Open your claude_desktop_config.json and add the server entry. The command points to the tp-mcp binary in your virtual environment.

{
  "mcpServers": {
    "trainingpeaks": {
      "command": "/absolute/path/to/trainingpeaks-mcp/.venv/bin/tp-mcp",
      "args": ["serve"]
    }
  }
}
5

Restart Claude Desktop and verify

Restart Claude Desktop. Ask Claude to retrieve your recent workouts or current fitness metrics to confirm all 64 tools are accessible.

TrainingPeaks Examples

Client configuration (Claude Desktop)

Replace the command path with the absolute path to tp-mcp in your virtual environment. Run 'which tp-mcp' after activating your venv to find it.

{
  "mcpServers": {
    "trainingpeaks": {
      "command": "/Users/yourname/trainingpeaks-mcp/.venv/bin/tp-mcp",
      "args": ["serve"]
    }
  }
}

Prompts to try

Query and manage your TrainingPeaks data using natural language with Claude.

- "Show me my CTL, ATL, and TSB fitness metrics for the past 4 weeks"
- "Build me a 4x8min threshold workout for Tuesday with a 10-minute warm-up and cool-down"
- "What are my best power PRs in the last 6 months?"
- "Log my weight at 74.5kg and sleep at 7.5 hours for today"
- "Set my FTP to 310 watts and recalculate my power zones"

Troubleshooting TrainingPeaks

tp-mcp auth fails to find cookies in the browser

Ensure you have an active TrainingPeaks login session in Chrome before running tp-mcp auth --from-browser chrome. The browser must be closed or the cookies database unlocked. If Chrome is running, try closing it first, or use the manual paste flow: tp-mcp auth (without --from-browser).

Claude Desktop cannot find the tp-mcp binary

Use the absolute path to the binary inside your virtual environment (e.g., /Users/yourname/trainingpeaks-mcp/.venv/bin/tp-mcp). The 'command' field in claude_desktop_config.json must be a full path — relative paths and PATH lookups are not reliable in the Claude Desktop subprocess environment.

Authentication expires and tools start returning 401 errors

TrainingPeaks session cookies eventually expire. Re-run 'tp-mcp auth --from-browser chrome' after logging into TrainingPeaks in Chrome to refresh the stored credentials, then restart Claude Desktop.

Frequently Asked Questions about TrainingPeaks

What is TrainingPeaks?

TrainingPeaks is a Model Context Protocol (MCP) server that trainingpeaks mcp server for claude desktop, code and cowork. no api approval needed - works with any account. query workouts, ctl/atl/tsb fitness data, power prs via natural language. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install TrainingPeaks?

Follow the installation instructions on the TrainingPeaks GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with TrainingPeaks?

TrainingPeaks works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is TrainingPeaks free to use?

Yes, TrainingPeaks is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "trainingpeaks-mcp": { "command": "npx", "args": ["-y", "trainingpeaks-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use TrainingPeaks?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides