Intervals.icu MCP Server

A Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude, ChatGPT, and other LLMs.

Originally based on eddmann/intervals-icu-mcp (MIT licensed). This project is an independent continuation with significant bug fixes and new features — see CHANGELOG.md for details.

Overview

58 tools spanning activities, activity analysis, activity messages, athlete profile, wellness, events/calendar, performance curves, workout library, gear, sport settings, and custom items — plus 4 MCP Resources (athlete profile, workout syntax, event categories, custom item schemas) and 7 MCP Prompts (training analysis, recovery check, weekly planning, and more). See Available Tools for the per-category breakdown.

Quick Start

Or for Claude Desktop, in 30 seconds:

1. Get your API key and athlete ID
2. Add this to your Claude Desktop config:

{
  "mcpServers": {
    "intervals-icu": {
      "command": "uvx",
      "args": ["intervals-icu-mcp"],
      "env": {
        "INTERVALS_ICU_API_KEY": "your-api-key-here",
        "INTERVALS_ICU_ATHLETE_ID": "i123456"
      }
    }
  }
}

3. Restart Claude and ask "Show me my activities from the last 7 days."

Prefer Claude Code, Cursor, or ChatGPT? See Client Configuration. Want to run from source or with Docker? See Installation & Setup.

Prerequisites

Install uv — it handles Python, dependencies, and execution in one tool. brew install uv on macOS/Linux, or powershell -c "irm https://astral.sh/uv/install.ps1 | iex" on Windows. From there, uvx fetches Python and the package automatically. Docker is also supported as an alternative.

Intervals.icu API Key Setup

Before installation, obtain your Intervals.icu API key:

1. Go to https://intervals.icu/settings → Developer → Create API Key.
2. Copy the key, and note your Athlete ID from your profile URL (format: i123456).

Installation

Nothing to install separately if you use the recommended setup. uvx (which ships with uv) automatically downloads and caches the intervals-icu-mcp package the first time your MCP client launches it — just paste the config snippet from Client Configuration into your client and you're done.

git clone https://github.com/hhopke/intervals-icu-mcp.git
cd intervals-icu-mcp
uv sync
uv run intervals-icu-mcp-auth  # interactive credential setup; or create .env manually:
#   INTERVALS_ICU_API_KEY=your_api_key_here
#   INTERVALS_ICU_ATHLETE_ID=i123456

docker build -t intervals-icu-mcp .

# Interactive credential setup (creates intervals-icu-mcp.env in the current directory):
touch intervals-icu-mcp.env  # pre-create the file so Docker mounts it as a file, not a dir
docker run -it --rm \
  -v "$(pwd)/intervals-icu-mcp.env:/app/.env" \
  --entrypoint= intervals-icu-mcp:latest \
  python -m intervals_icu_mcp.scripts.setup_auth

Client Configuration

The server speaks MCP over stdio and works with any compliant client. Click a client to expand. If you followed Quick Start (uvx), use the first config block; if you used the source or Docker alternative above, use the matching variant inside the same collapsible.

{
  "mcpServers": {
    "intervals-icu": {
      "command": "uvx",
      "args": ["intervals-icu-mcp"],
      "env": {
        "INTERVALS_ICU_API_KEY": "your-api-key-here",
        "INTERVALS_ICU_ATHLETE_ID": "i123456"
      }
    }
  }
}

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

{
  "mcpServers": {
    "intervals-icu": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-v", "/ABSOLUTE/PATH/TO/intervals-icu-mcp.env:/app/.env", "intervals-icu-mcp:latest"]
    }
  }
}

claude mcp add intervals-icu --scope user \
  --env INTERVALS_ICU_API_KEY=your-key \
  --env INTERVALS_ICU_ATHLETE_ID=i123456 \
  -- uvx intervals-icu-mcp

{
  "mcpServers": {
    "intervals-icu": {
      "command": "uvx",
      "args": ["intervals-icu-mcp"],
      "env": {
        "INTERVALS_ICU_API_KEY": "your-api-key-here",
        "INTERVALS_ICU_ATHLETE_ID": "i123456"
      }
    }
  }
}

Delete Safety Mode

Destructive tools are gated by the optional INTERVALS_ICU_DELETE_MODE env var (safe / full / none, default safe). The gate is server-side and outside the model's reach — tools that aren't registered cannot be invoked. Safe mode refuses past-event deletion and gates delete_activity / delete_sport_settings / delete_custom_item entirely. See docs/tools.md for the full table, response envelope, and TZ-buffer rationale.

Remote Deployment (HTTP / SSE)

By default the server runs over stdio — the right transport for local clients like Claude Desktop, Claude Code, and Cursor. For remote deployment (hosted MCP, reverse proxy, Docker-on-a-server, ChatGPT connector), pass --transport:

# Streamable HTTP (recommended — used by ChatGPT and modern remote clients)
intervals-icu-mcp --transport http --host 127.0.0.1 --port 8000

# Legacy SSE (for clients that haven't moved to streamable HTTP yet)
intervals-icu-mcp --transport sse --host 127.0.0.1 --port 8000

⚠️ Security: do not expose an HTTP-mode server to untrusted networks.

The MCP protocol has no built-in authentication. Anyone who can reach the URL can exercise every tool with your credentials — read every activity, delete activities, modify your FTP, create calendar events, etc. Binding to 0.0.0.0 on a direct-exposed host (VPS, LAN with open port) is equivalent to publishing your Intervals.icu API key.

For remote access, prefer one of the following:

• Tailscale / Cloudflare Tunnel / ZeroTier — only your authenticated devices can reach the endpoint. Zero code changes, simplest option.
• Reverse proxy with auth (nginx + basic auth, Cloudflare Access, etc.) — terminates TLS and gates access.
• SSH tunnel — ssh -L 8000:localhost:8000 host if you just need occasional access from one machine.

Credentials are always read from INTERVALS_ICU_API_KEY and INTERVALS_ICU_ATHLETE_ID — use env vars (not a committed .env) when deploying to a shared host.

Usage

Ask Claude to interact with your Intervals.icu data in natural language. A few starter prompts:

"Show me my activities from the last 30 days"
"Am I overtraining? Check my CTL, ATL, and TSB"
"How's my recovery this week? Show HRV and sleep trends"
"Create a sweet spot cycling workout for tomorrow"
"What's my 20-minute power and FTP?"

For the full catalogue of example prompts by category, see docs/examples.md.

Available Tools

58 tools, 4 resources, and 7 prompt templates. One-line summary below — full reference in docs/tools.md.

Documentation

• Example prompts — full catalogue of natural-language prompts by category
• Tool reference — complete tool, resource, and prompt inventory
• Architecture overview — how the server, middleware, client, and tools fit together
• Testing guide — conventions for pytest + respx, fixtures, and running the suite
• Changelog — release history
• Adding a new tool — step-by-step workflow for contributors

Contributing

Issues and pull requests are welcome. Before opening a PR, run make can-release locally to match what CI enforces (ruff, pyright, pytest). For new tools, follow the pattern in .claude/skills/add-tool/SKILL.md and add a respx-mocked test file alongside the implementation.

License

MIT License - see the LICENSE file for details.

Disclaimer

This project is not affiliated with, endorsed by, or sponsored by Intervals.icu. All product names, logos, and brands are property of their respective owners.