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 trainingpeaksConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use TrainingPeaks
The TrainingPeaks MCP server gives Claude direct access to your TrainingPeaks training data through 64 MCP tools covering workouts, fitness metrics (CTL/ATL/TSB), power and running PRs, athlete settings, health metrics, equipment, and calendar events. Unlike official API integrations, it uses browser-extracted session cookies so no API approval is needed — any TrainingPeaks account works. Athletes and coaches use it to analyze training load, build structured workouts, schedule events, and query fitness trends through natural language conversations with Claude.
Prerequisites
- Python 3.10 or later installed
- A TrainingPeaks account (free or paid; no API approval needed)
- Google Chrome or another supported browser with an active TrainingPeaks login session for cookie extraction
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
Clone the repository and create a virtual environment
Clone the project from GitHub, then create and activate a Python virtual environment to keep dependencies isolated.
git clone https://github.com/JamsusMaximus/trainingpeaks-mcp.git
cd trainingpeaks-mcp
python3 -m venv .venv
source .venv/bin/activateInstall the package
Install the package and its dependencies in editable mode inside the virtual environment.
pip install -e .Authenticate with TrainingPeaks
Run the authentication command to extract cookies from your browser. The --from-browser flag reads cookies automatically from Chrome (or specify firefox, edge). Alternatively run 'tp-mcp auth' for manual cookie entry. Credentials are stored securely in your OS keychain.
tp-mcp auth --from-browser chromeNote the virtual environment path
You will need the full path to the tp-mcp binary inside your virtual environment for the Claude Desktop config. Run 'which tp-mcp' after activating the venv to get this path.
which tp-mcpAdd to Claude Desktop configuration
Open ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows) and add the trainingpeaks server entry using the full path to the tp-mcp binary.
{
"mcpServers": {
"trainingpeaks": {
"command": "/path/to/.venv/bin/tp-mcp",
"args": ["serve"]
}
}
}Restart Claude Desktop and test
Restart Claude Desktop so it picks up the new server. Ask Claude about your recent workouts to confirm the connection is working.
TrainingPeaks Examples
Client configuration
Claude Desktop config entry for the TrainingPeaks MCP server. Replace the command path with the actual path from 'which tp-mcp' in your venv.
{
"mcpServers": {
"trainingpeaks": {
"command": "/Users/yourname/trainingpeaks-mcp/.venv/bin/tp-mcp",
"args": ["serve"]
}
}
}Prompts to try
Example natural-language prompts for querying and managing your TrainingPeaks data through Claude.
- "What is my current CTL, ATL, and TSB? Am I in a peak or recovery phase?"
- "Show me my power PRs for 5-second, 1-minute, 5-minute, and 20-minute efforts"
- "Build me a 4x8-minute threshold interval session for Tuesday with warm-up and cool-down"
- "What was my weekly TSS last week compared to my ATP target?"
- "Schedule an easy recovery ride for Saturday at 8am and add a note about post-race fatigue"
- "Update my FTP to 310 watts and recalculate my power training zones"Troubleshooting TrainingPeaks
Authentication fails or cookies expire after a few days
Re-run 'tp-mcp auth --from-browser chrome' after logging into TrainingPeaks in Chrome. Session cookies expire periodically; repeating this command refreshes them. Make sure Chrome is closed or at least the TrainingPeaks tab is loaded when running the command.
Claude Desktop cannot find the tp-mcp command
The command in the config must be an absolute path to the tp-mcp binary inside the virtual environment, not just 'tp-mcp'. Run 'which tp-mcp' while the venv is active to get the correct full path, and paste that into the config.
Tools return empty data or 'no workouts found'
Confirm your TrainingPeaks account has recorded activities. If using a basic/free account, some metrics like CTL/ATL/TSB require a Premium subscription. Also re-authenticate if it has been more than a week since the last auth run.
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. 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.