About Garmin Connect (treinos)
Garmin Connect (treinos) is an MCP service for clients such as Claude and Cursor to access structured Garmin workouts. It covers running, cycling, swimming, and multisport training; the README describes it as read-only but lists no available tools.
Key features
- 01Workout data across sports
- 02Connects through Garmin sessions
- 03Works with MCP clients
Use cases
- 01Review upcoming workouts
- 02Look up running or cycling workouts
MCP support
This MCP service is available to clients that support MCP over HTTP. The README lists zero available tools and describes the service as read-only.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.mcp.ai/p_garminclaude mcp add --transport http dir-garmin https://api.mcp.ai/p_garmin{"mcpServers":{"dir-garmin":{"type":"http","url":"https://api.mcp.ai/p_garmin"}}}Open in Cursor{"servers":{"dir-garmin":{"type":"http","url":"https://api.mcp.ai/p_garmin"}}}Open in VS Code{"mcpServers":{"dir-garmin":{"type":"http","url":"https://api.mcp.ai/p_garmin"}}}{"mcpServers":{"dir-garmin":{"serverUrl":"https://api.mcp.ai/p_garmin"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
16| Parameter | Type | Required | Description |
|---|---|---|---|
| account | string | No |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.