Intervals.icu MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Intervals.icu MCP ServerWhat were my activities last week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Intervals.icu MCP Server
An MCP (Model Context Protocol) server that connects Claude to the Intervals.icu training platform. Query your training data, create workouts, manage your calendar, and coach athletes — all through natural language in Claude Desktop.
Features
Tools (18)
Tool | Description |
| List all athletes you coach |
| Get athlete profile (weight, FTP, zones) |
| List activities in a date range |
| Get detailed info for a single activity |
| Get time-series data (power, HR, cadence, etc.) |
| Get intervals/laps for an activity |
| Get wellness data (weight, HRV, sleep, mood) for a date range |
| Get wellness data for a specific day |
| Update wellness data for a day |
| Get calendar events (planned workouts, notes, targets) |
| Create a workout, note, target, or race on the calendar |
| Update an existing calendar event |
| Delete a calendar event |
| List workouts from the workout library |
| Create a workout in the library |
| Get FTP, LTHR, zones for all sports |
| List all gear (bikes, shoes, etc.) |
| Get best power/pace curves for a date range |
All tools that operate on athlete data accept an optional athlete_id parameter, so coaches can query and manage data for any of their athletes.
Prompt Templates (3)
Available via the attachment icon (📎) in Claude Desktop:
analyze_training — Full training analysis: volume, intensity distribution, load/recovery trends, wellness, overtraining risk
plan_training — Create a periodized training plan based on recent data, with customizable instructions
weekly_report — Weekly report comparing planned vs. actual training with wellness trends
Related MCP server: intervals.mcp
Setup
Prerequisites
Node.js v18+
An Intervals.icu account
1. Get your Intervals.icu credentials
Go to Intervals.icu → Settings → Developer Settings
Copy your API Key
Copy your Athlete ID (e.g.
i12345)
2. Install and build
git clone https://github.com/lmolema/intervals-mcp.git
cd intervals-mcp
npm install
npm run build3. Configure Claude Desktop
Add the following to your Claude Desktop config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"intervals-icu": {
"command": "node",
"args": ["/absolute/path/to/intervals-mcp/dist/index.js"],
"env": {
"INTERVALS_API_KEY": "your_api_key_here",
"INTERVALS_ATHLETE_ID": "your_athlete_id_here"
}
}
}
}Replace the path and credentials with your own values.
4. Restart Claude Desktop
The Intervals.icu tools should now appear in Claude Desktop.
Usage Examples
Just ask Claude in natural language:
"What were my activities last week?"
"How is my fitness trend this month?"
"Show my athletes"
"Analyze my athlete's training over the past 4 weeks"
"Create a 60-minute easy run for Tuesday"
"Plan 4 weeks of training for my athlete, Tuesday short, Friday long, no intervals"
Workout Syntax
When creating workouts, the server uses the Intervals.icu workout text format. Claude knows this syntax and will generate it correctly. Some examples:
Easy run:
-60' 75-85% pace
DL with zone blocks:
-15' Z1 pace
-15' Z2 pace
-15' Z3 pace
-15' Z1 pace
Interval session (8x600mtr):
-15' wu Z1 pace press lap
8x
-600mtr 94-98% pace
-90" rest Z1 pace
-15' cd Z1 pace press lapCoaching
If you coach athletes on Intervals.icu, all tools work with their data too. Use list_athletes to find their IDs, then pass athlete_id to any tool — or just refer to them by name and Claude will figure it out.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Connect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing.
Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport. Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.
Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.
Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.
Related MCP Servers
- AlicenseAqualityCmaintenanceConnects Claude with the Intervals.icu API to retrieve fitness data including activities, workouts, wellness metrics, and training events.10341GPL 3.0
- FlicenseAqualityCmaintenanceEnables AI assistants to access and analyze intervals.icu training data including activities, fitness metrics (CTL/ATL/TSB), wellness stats, and calendar events. Supports natural language querying of athletic performance for training insights and workout planning.6
- AlicenseNot gradedqualityBmaintenanceBrings Garmin training data into Claude via Intervals.icu, enabling querying of activities, wellness, and planned workouts, as well as creating structured workouts that sync back to the Garmin watch.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude AI to access and manage intervals.icu training data, including workouts, wellness, and fitness trends, through natural language conversation.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ascuitando/intervals-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server