TrainingPeaks
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.
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
Maintainer
Works with
Installation
Manual Installation
npx trainingpeaks-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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 .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 authGenerate 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 configAdd 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"]
}
}
}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.
TrainingPeaks Alternatives — Similar Analytics Servers
Looking for alternatives to TrainingPeaks? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
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.
Set Up TrainingPeaks in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.