Intervals.icu MCP Server
@mvilanova
About Intervals.icu MCP Server
Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"intervals-mcp-server": {
"command": "uv",
"args": [
"venv",
"--python",
"3.12"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Intervals.icu MCP Server?
The Intervals.icu MCP Server is a Model Context Protocol (MCP) server that connects Claude and ChatGPT with the Intervals.icu API. It provides tools for authentication and data retrieval for activities, events, wellness data, power curves, and custom items.
How to use Intervals.icu MCP Server?
Install Python 3.12+, clone the repository, create a virtual environment with uv venv --python 3.12, sync dependencies with uv sync, then set API_KEY and ATHLETE_ID in a .env file. Configure Claude Desktop by adding the server to claude_desktop_config.json using the uv command, or start the server in SSE mode for ChatGPT using environment variables MCP_TRANSPORT=sse and FASTMCP_HOST/FASTMCP_PORT.
Key features of Intervals.icu MCP Server
- Retrieve and manage activities, events, and wellness data
- Access interval details, streams, and power curves
- Create, update, delete custom items (charts, fields, zones)
- Supports both stdio (Claude) and SSE (ChatGPT) transports
Use cases of Intervals.icu MCP Server
- Ask Claude about your past training sessions and performance
- Manage upcoming workouts, races, or notes via ChatGPT
- Automate wellness data logging and analysis
- Integrate custom items and power curve data into AI workflows
FAQ from Intervals.icu MCP Server
What are the runtime requirements?
Python 3.12 or higher, the MCP Python SDK, httpx, and python-dotenv. Use uv for package management.
How do I get my Intervals.icu API key and athlete ID?
Log in to Intervals.icu, go to Settings > API to generate a key. Your athlete ID is visible in the URL (e.g., https://intervals.icu/athlete/i12345/...).
Which transports are supported?
Stdio for Claude Desktop and SSE for ChatGPT’s beta MCP connectors. For SSE, set MCP_TRANSPORT=sse and expose the server (e.g., via ngrok).
Why does Claude Desktop give a spawn uv ENOENT error?
Claude cannot find the uv executable. Use the full path to uv (get it with which uv or where.exe uv) in the command field of claude_desktop_config.json.
Where does Claude Desktop store its config on Windows?
If installed from the Microsoft Store, the config is at AppData\Local\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\claude_desktop_config.json. Otherwise, it is in AppData\Roaming\Claude\.
More AI & Agents MCP servers
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
Perplexity MCP Server
DaInfernalCoderA Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon
Comments