MCP Integration Overview

FitRepo exposes a Model Context Protocol (MCP) server that lets AI assistants query your training data directly. Once configured, you can ask questions like:

“What was my CTL when I started my marathon block?” “Show me my best 20-minute power over the last 6 months.” “How does my HRV trend around hard training weeks?”

How it works

Claude Desktop  ──stdio──►  fitrepo-mcp (npm package)
                                │
                                │ HTTPS + Bearer token
                                ▼
                         FitRepo API (mydatafor.life)
                                │
                                ▼
                         Your Supabase database

The MCP server is a small Node.js binary (@fitrepo/mcp-server) that runs locally on your machine. It communicates with Claude Desktop over stdio (the standard MCP transport) and forwards requests to the FitRepo API using your personal API key.

Your data never passes through Anthropic’s servers — Claude only receives the query results that you’ve explicitly fetched from your own account.

Available tools

The server exposes 7 tools:

Tool	Description
list_activities	Paginated activity list with sport/date filters
get_activity	Full detail for a single activity
get_fitness_timeline	CTL/ATL/TSB for a date range
get_best_efforts	All-time and per-activity mean-maximal power
get_wellness	HRV, RHR, sleep, and readiness logs
get_thresholds	FTP and LTHR history
get_profile	Athlete profile (age, weight, sex)

See the Tools Reference for full parameter documentation.

Prerequisites

• A FitRepo account with at least one synced activity
• Node.js 18 or later installed locally
• Claude Desktop (or another MCP-compatible client)

Next step

Follow the Setup guide to generate your API key and configure Claude Desktop.