Intervals

v1.0.0Analyticsstable

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

intervalsmcpai-integration
Share:
270
Stars
0
Downloads
0
Weekly
0/5

What is Intervals?

Intervals is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for connecting claude and chatgpt with the intervals.icu api.

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

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Model Context Protocol (MCP) server for connecting Claude an

Use Cases

Access fitness tracking and training data
Analyze athletic performance metrics
mvilanova

Maintainer

LicenseGPL-3.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx intervals

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Intervals

The Intervals.icu MCP server connects AI assistants like Claude and ChatGPT to your Intervals.icu fitness and training data, enabling natural language queries over your workouts, wellness metrics, power curves, and training events. It provides 13 tools covering activities, intervals, streams, wellness data, and event management, all authenticated via your Intervals.icu API key. Athletes and coaches use it to analyze training trends, compare power outputs across training blocks, and manage their event calendars through conversational AI.

Prerequisites

  • Python 3.12 or higher
  • uv package manager installed
  • An Intervals.icu account with an API key (Settings > API)
  • Your Intervals.icu athlete ID (from your profile URL, e.g. i12345)
  • An MCP-compatible client such as Claude Desktop
1

Install uv package manager

The Intervals.icu MCP server uses uv for dependency management and execution. Install it before proceeding.

curl -LsSf https://astral.sh/uv/install.sh | sh
2

Clone the repository and set up the environment

Clone the intervals-mcp-server repository, create a virtual environment with Python 3.12, and install dependencies.

git clone https://github.com/mvilanova/intervals-mcp-server.git
cd intervals-mcp-server
uv venv --python 3.12
source .venv/bin/activate
uv sync
3

Create your .env file with credentials

Copy the example env file and fill in your Intervals.icu API key and athlete ID. Find your API key at intervals.icu/settings and your athlete ID in your profile URL.

cp .env.example .env
# Edit .env:
# API_KEY=your_intervals_icu_api_key
# ATHLETE_ID=i12345
# INTERVALS_API_BASE_URL=https://intervals.icu/api/v1
# LOG_LEVEL=INFO
4

Register the MCP server with Claude Desktop

Use the mcp install command to register the server. It reads your .env file and configures Claude Desktop automatically.

mcp install src/intervals_mcp_server/server.py --name "Intervals.icu" --with-editable . --env-file .env
5

Restart Claude Desktop and verify

Restart Claude Desktop after installation. The Intervals.icu server should appear in the connected MCP servers list and you can begin querying your training data.

Intervals Examples

Client configuration

Claude Desktop config for the Intervals.icu MCP server using uv to run the server with an env file.

{
  "mcpServers": {
    "intervals-icu": {
      "command": "/path/to/uv",
      "args": [
        "run",
        "--with-editable",
        "/path/to/intervals-mcp-server",
        "python",
        "/path/to/intervals-mcp-server/src/intervals_mcp_server/server.py"
      ],
      "env": {
        "API_KEY": "your_intervals_icu_api_key",
        "ATHLETE_ID": "i12345",
        "INTERVALS_API_BASE_URL": "https://intervals.icu/api/v1"
      }
    }
  }
}

Prompts to try

Sample prompts for querying your Intervals.icu training and wellness data.

- "Show me my last 10 cycling activities with average power and duration"
- "How has my weekly training load changed over the past 3 months?"
- "What is my 20-minute power curve from the last 90 days of cycling?"
- "Summarize my wellness data (HRV, sleep, weight) for the past two weeks"
- "Add a rest day event to my Intervals.icu calendar for next Monday"

Troubleshooting Intervals

Authentication error — 401 Unauthorized from the Intervals.icu API

Verify that your API_KEY in .env is correct and has not been revoked. Generate a new key at intervals.icu Settings > API. Also confirm that ATHLETE_ID matches the prefix in your Intervals.icu profile URL (e.g. i12345).

Python version error — requires Python 3.12+

Use uv to create a virtual environment pinned to Python 3.12: uv venv --python 3.12. If Python 3.12 is not installed, uv can install it: uv python install 3.12.

Server starts but no tools appear in Claude Desktop

Check that the mcp install command completed without errors and that Claude Desktop was fully restarted (not just the window). On Windows, use the full path to uv.exe in the config JSON and use double backslashes for directory separators.

Frequently Asked Questions about Intervals

What is Intervals?

Intervals is a Model Context Protocol (MCP) server that model context protocol (mcp) server for connecting claude and chatgpt with the intervals.icu api. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Intervals?

Follow the installation instructions on the Intervals GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Intervals?

Intervals works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Intervals free to use?

Yes, Intervals is open source and available under the GPL-3.0 license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "intervals": { "command": "npx", "args": ["-y", "intervals"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Intervals?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides