mvilanova/intervals-mcp-server

What it solves

This project provides a bridge between AI assistants like Claude and ChatGPT and the Intervals.icu API. It allows users to query and manage their athletic training data, wellness metrics, and event schedules directly through a conversational interface.

How it works

It is implemented as a Model Context Protocol (MCP) server. By connecting the server to an AI client, the AI gains access to a set of specialized tools to interact with the Intervals.icu API using the user's athlete ID and API key. It supports both local execution for Claude Desktop and SSE transport for ChatGPT.

Who it’s for

Athletes and coaches who use Intervals.icu for training tracking and want to use LLMs to analyze their activities, power curves, and wellness data or manage their calendar of events.

Highlights

• Comprehensive Data Access: Retrieves activities, detailed interval data, raw data streams (power, heart rate), and athlete power curves.
• Wellness and Event Management: Fetches wellness data and allows for creating, updating, and deleting events (workouts, races).
• ** uma custom items**: Supports managing custom items such as charts and zones.
• Multi-Client Support: Compatible with Claude Desktop and ChatGPT's MCP connectors.