garmin-mcp

garmin-mcp

Exposes your Garmin Connect data (activities, sleep, recovery, training status) to Claude in read-only mode.

Category
Visit Server

README

MCP Garmin

Servidor MCP que expone tus datos de Garmin Connect (actividades, sueño, recuperación, estado de forma) a Claude, en modo solo lectura.

Instalación rápida (Claude Desktop, sin terminal)

  1. Descarga mcp-garmin.mcpb de la última release.
  2. En Claude Desktop: Configuración → Extensiones → "Install Extension…" → selecciona el fichero.
  3. Rellena tu email y contraseña de Garmin Connect en el formulario. Se guardan solo en tu máquina.

Instalación para desarrollo

git clone <url-del-repo>
cd mcp-garmin
cp .env.example .env   # rellena tus credenciales
uv sync
uv run pytest          # verifica que todo pasa

Añade el servidor a tu claude_desktop_config.json o .mcp.json apuntando a uv run --directory <ruta-del-repo> src/server.py.

Tools disponibles

  • garmin_login(email, password, mfa_code) — inicia sesión (con soporte MFA).
  • get_activities(start, limit, activity_type) — actividades recientes.
  • get_activity_detail(activity_id) — detalle y splits de una actividad.
  • get_daily_summary(start_date, end_date) — pasos, calorías, minutos activos.
  • get_recovery_metrics(day) — sueño, Body Battery, HRV, FC en reposo.
  • get_training_zones() — zonas de FC y potencia configuradas.
  • get_training_status(day) — Training Load/Status, VO2 max, récords, predicciones.

Alcance

Solo lectura. La escritura de entrenamientos hacia el dispositivo queda fuera de esta versión (ver docs/superpowers/specs/2026-07-27-garmin-mcp-connector-design.md).

Notas sobre credenciales y requisitos

  • Instalación vía .mcpb: Claude Desktop guarda tu email y contraseña de Garmin usando el keychain del sistema operativo (cifrado). Instalación manual (editando claude_desktop_config.json / .mcp.json o el .env): GARMIN_PASSWORD se guarda tal cual, en texto plano, en ese fichero. Es un compromiso asumido para simplificar el flujo de desarrollo/manual; ten cuidado con los permisos de esos ficheros y no los subas a un repo.
  • Requisito de uv en la máquina destino: el .mcpb usa "type": "uv" como runtime, lo que evita tener que preinstalar Python o Node en la máquina, pero no evita necesitar uv: uv debe estar instalado en la máquina donde se instale la extensión para que mcpb pueda ejecutar el servidor.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured