Garmin Connect 러닝 데이터를 LLM에 제공하는 MCP(Model Context Protocol) 서버입니다.
Garmin Connect MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Garmin Connect MCP directly instead of describing what you should do. Garmin Connect 러닝 데이터를 LLM에 제공하는 MCP(Model Context Protocol) 서버입니다.
Once Garmin Connect MCP is connected, these are the calls the assistant has available:
GARMIN_EMAIL — Garmin Connect 이메일GARMIN_PASSWORD — Garmin Connect 비밀번호GARMIN_TOKEN_DIR — 토큰 저장 경로GARMINTOKENS — Base64 인코딩 토큰 (CI/Docker용)get_recent_activities — 최근 러닝 활동 목록 (GAP, RWD 포함)get_activities_by_date — 날짜 범위로 러닝 활동 조회get_activity_detail — 활동 상세 정보 (스태미나, 임팩트 로드 포함)get_activity_splits — km별 스플릿 데이터get_activity_weather — 활동 중 날씨 조건 (온도, 습도, 풍속)get_activity_typed_splits — ClimbPro 경사 구간 분석 (등급, GAP)get_weekly_running_summary — 주간 러닝 요약get_monthly_running_summary — 월간 러닝 요약 + 전월 비교Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Garmin Connect MCP's toolset — GARMIN_EMAIL, GARMIN_PASSWORD, GARMIN_TOKEN_DIR and 11 more — is a fair guide to whether it matches your workflow. It is maintained by leewnsdud; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| GARMIN_EMAIL | Garmin Connect 이메일 |
| GARMIN_PASSWORD | Garmin Connect 비밀번호 |
| GARMIN_TOKEN_DIR | 토큰 저장 경로 |
| GARMINTOKENS | Base64 인코딩 토큰 (CI/Docker용) |
| get_recent_activities | 최근 러닝 활동 목록 (GAP, RWD 포함) |
| get_activities_by_date | 날짜 범위로 러닝 활동 조회 |
| get_activity_detail | 활동 상세 정보 (스태미나, 임팩트 로드 포함) |
| get_activity_splits | km별 스플릿 데이터 |
| get_activity_weather | 활동 중 날씨 조건 (온도, 습도, 풍속) |
| get_activity_typed_splits | ClimbPro 경사 구간 분석 (등급, GAP) |
| get_weekly_running_summary | 주간 러닝 요약 |
| get_monthly_running_summary | 월간 러닝 요약 + 전월 비교 |
| get_training_status | 훈련 상태 |
| get_training_readiness | 훈련 준비도 점수 |
{
"mcpServers": {
"garmin-mcp": {
"command": "/Users/<username>/.local/bin/uv",
"args": [
"--directory",
"/path/to/garmin-mcp",
"run",
"garmin-mcp"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.