mvilanova/intervals-mcp-server

Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.

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.

Related

  • Project
    Taxuspt/garmin_mcp

    A Model Context Protocol (MCP) server that connects Garmin Connect to AI assistants, enabling users to query fitness data, manage workouts, and analyze performance metrics via natural language.

  • Project
    atilaahmettaner/tradingview-mcp

    A Python‑only server that exposes 39 market‑data, technical‑analysis, screener and back‑testing tools via the Model Context Protocol (MCP). AI assistants (Claude, ChatGPT, Cursor, Copilot, etc.) can call these tools with natural language prompts and receive live data, indicator tables, or interactive charts inside the chat. Self‑hosted for free (MIT license) or available as a hosted SaaS (TradingMCP) for $9 / mo.

  • Project
    chrisdoc/hevy-mcp

    Hevy MCP is an open‑source Model Context Protocol server that exposes the Hevy fitness‑tracking API as 23 AI‑friendly tools (read and write). It can run as a Cloudflare Worker (hosted endpoint) or locally via npm/Docker, letting assistants like Claude, Codex, or Cursor analyse workouts, summarize training, search routines, and even create or update workouts and body‑measurements—all under user‑controlled authentication (API key or OAuth).

  • Project
    motherduckdb/mcp-server-motherduck

    A self‑hosted MCP server that wraps DuckDB (local, S3, or MotherDuck) so AI assistants can run SQL queries via the Model‑Chat‑Protocol. Supports stdio or HTTP, read/write control, Docker deployment, and integrates with Claude, Gemini, Cursor, etc.

  • Project
    pab1it0/prometheus-mcp-server

    A Model Context Protocol server that enables AI assistants to query, explore, and analyze Prometheus metrics using PromQL.