MCP Catalogs
Homeintervals-icu-mcp screenshot

intervals-icu-mcp

by eddmann·25·Score 43

Comprehensive MCP server for Intervals.icu integration with 48 tools for training data, wellness metrics, and performance analysis.

productivityhealthai-llm
22
Forks
12
Open issues
6 mo ago
Last commit
2d ago
Indexed

Overview

This MCP server provides extensive integration with Intervals.icu, a cycling and running training platform. It offers comprehensive access to user data through 48 tools organized into 9 categories including activities, performance analysis, wellness tracking, calendar management, and gear management. The server includes not only tools for data manipulation but also a persistent athlete profile resource and 6 pre-built prompt templates for common training scenarios.

Try asking AI

After installing, here are 7 things you can ask your AI assistant:

you:Analyze cycling or running performance metrics and training data
you:Plan and manage workout schedules and training events
you:Track wellness metrics including recovery, sleep, and HRV
you:Manage cycling and running gear with maintenance tracking
you:Review historical activities and performance curves
you:What authentication method does this MCP server use?
you:Can I use this server with other LLM clients besides Claude?

When to choose this

Choose this server if you're a serious cyclist or runner using Intervals.icu for training data and want AI assistance with training analysis and planning.

When NOT to choose this

Don't choose this if you don't use Intervals.icu for training or prefer a more general-purpose fitness tracking platform integration.

Tools this server exposes

12 tools extracted from the README
  • get-activity-details

    Get comprehensive details for a specific activity

  • get-activity-streams

    Get time-series data (power, HR, cadence, altitude, GPS)

  • get-best-efforts

    Find peak performances across all durations in an activity

  • get-athlete-profile

    Get athlete profile with fitness metrics and sport settings

  • get-wellness-data

    Get recent wellness metrics with trends (HRV, sleep, mood, fatigue)

  • get-calendar-events

    Get planned events and workouts from calendar

  • create-event

    Create new calendar events (workouts, races, notes, goals)

  • get-power-curves

    Analyze power curves with FTP estimation and power zones

  • get-workout-library

    Browse workout folders and training plans

  • get-gear-list

    Get all gear items with usage and status

  • update-sport-settings

    Update FTP, FTHR, pace threshold, or zone configuration

  • download-activity-file

    Download original activity file

Comparable tools

strava-mcpgarmin-mcpfitness-tracker-shell-mcp

Installation

Installation

Prerequisites

  • Python 3.11+ and [uv](https://github.com/astral-sh/uv), OR
  • Docker

Authentication Setup

  1. Get your Intervals.icu API key from https://intervals.icu/settings
  2. Note your Athlete ID from your profile URL (format: i123456)

Option 1: Using UV

cd intervals-icu-mcp
uv sync

# Configure credentials
uv run intervals-icu-mcp-auth

Option 2: Using Docker

docker build -t intervals-icu-mcp .

# Create and configure env file
touch intervals-icu-mcp.env
docker run -it --rm -v "$(pwd)/intervals-icu-mcp.env:/app/.env" intervals-icu-mcp:latest python -m intervals_icu_mcp.scripts.setup_auth

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "intervals-icu": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/ABSOLUTE/PATH/TO/intervals-icu-mcp",
        "intervals-icu-mcp"
      ]
    }
  }
}

FAQ

What authentication method does this MCP server use?
The server uses API key authentication with HTTP Basic Auth (username 'API_KEY' with your key as password). No OAuth required.
Can I use this server with other LLM clients besides Claude?
Yes, as long as the client supports the Model Context Protocol (MCP), you can use this server with any compatible LLM client.

Compare intervals-icu-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.