An MCP server for Intervals.icu that lets LLM clients access and manage training data, wellness metrics, performance analysis, workouts, events, gear, and profile information. It supports local stdio use as well as remote HTTP/SSE deployment with the user's Intervals.icu API key and athlete ID.
From the registry: MCP server for Intervals.icu — access training, wellness, and performance data from LLMs.

$ brew install uvhttps://github.com/astral-sh/uv},{Please install the `intervals-icu-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install uv** — Install uv, which provides uvx for running the MCP server package without a separate manual install. Run: `brew install uv` (https://github.com/astral-sh/uv},{)
- **INTERVALS_ICU_ATHLETE_ID** — Your Intervals.icu athlete ID from your profile URL (format like i123456). (https://intervals.icu/settings)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["intervals-icu-mcp"]
- required environment variables:
- `INTERVALS_ICU_API_KEY`: Your Intervals.icu API key used to authenticate requests. (example: `<your-api-key>`)
- `INTERVALS_ICU_ATHLETE_ID`: Your Intervals.icu athlete ID. (example: `<your-athlete-id>`)
Note: Recommended install path is via uvx. The README also documents alternative source, Docker, HTTP, and SSE modes, but stdio via uvx is the simplest portable MCP client configuration. The server can also be run remotely with `intervals-icu-mcp --transport http` or `--transport sse`, with the same INTERVALS_ICU_API_KEY and INTERVALS_ICU_ATHLETE_ID environment variables.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.INTERVALS_ICU_API_KEYrequiredIntervals.icu API key used to authenticate requestsINTERVALS_ICU_ATHLETE_IDrequiredIntervals.icu athlete ID (for example, i123456)AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.