Fitness AI Connector

Fitness AI Connector

Garmin health and fitness data in Claude and ChatGPT via the official Garmin Health API. Hosted remote server with OAuth sign-in — no password sharing.

Category
访问服务器

README

Fitness AI Connector

Talk to your Garmin data in Claude and ChatGPT.

Connect your Garmin health and fitness data to Claude and ChatGPT through the official Garmin Health API. Hosted remote MCP server (Streamable HTTP) with OAuth 2.0 sign-in — your Garmin password is never shared. 12 tools: daily health summary (sleep, HRV, stress, Body Battery), activities with lap and time-series analysis, body composition, menstrual cycle tracking, trends, and on-demand data refresh. 3,000+ users and 150+ paid subscribers as of July 2026. Free tier available.

🌐 Website: https://fmp.it.com/en/fitness-ai/

How it works

  1. Connect the app in ChatGPT (Apps Directory) or add the connector in Claude
  2. Sign in on Garmin's own page (OAuth 2.0 + PKCE) — we never see or store your password
  3. Ask questions in plain language: "How did I sleep this week?", "Show the details of my latest run", "Am I improving?"

Your Garmin data syncs automatically via the Garmin Health API webhook/pull model. You can disconnect from your Garmin account settings or delete all data at any time.

What you can ask

Area Examples
Daily wellness Steps, calories, heart rate, sleep stages & score, stress, Body Battery, HRV
Activities Runs, rides, swims with pace, distance, calories, heart rate per activity
Activity details Lap splits, HR drift, pace stability, negative splits, cadence & power stats
Body composition Weight, BMI, body fat %, muscle mass (smart scale required)
Menstrual cycle Cycle phase, day in cycle, fertile window, period tracking (opt-in in Garmin Connect)
Long-term trends Weekly averages, directional changes, "am I improving?" comparisons
Profile & account Connection status, VO2max, fitness age, subscription management

Tools

The connector exposes 12 MCP tools:

  • get_user_profile — Garmin connection status, subscription tier, VO2max, and fitness age.
  • get_health_summary — Daily snapshot: steps, calories, heart rate, sleep stages & score, stress / Body Battery, HRV. Optional opt-in time series (heart rate, stress, Body Battery, sleep stages, SpO2, respiration).
  • get_activities — List activities (runs, rides, swims) with pace, distance, calories, and heart rate per activity.
  • get_activity_details — Lap splits, HR drift, pace stability, negative split ratio, cadence and power stats for one activity, plus optional per-second time series.
  • get_body_composition — Weight, BMI, body fat %, muscle mass, bone mass, body water % (smart scale required).
  • get_cycle_data — Menstrual cycle snapshots: phase, day in cycle, period start, cycle length (predicted vs actual), fertile window, with pregnancy semantics when applicable (cycle tracking must be enabled in Garmin Connect).
  • get_trends — Weekly averages, directional changes, and pattern detection ("am I improving?").
  • refresh_data — Re-fetch a range of Garmin data; dates before your connection date are skipped.
  • refetch_activity_detail — Request recovery of a missing activity detail.
  • manage_subscription — Billing portal and account deletion (30-day recovery).
  • get_help — Setup, troubleshooting, and billing FAQ answers.
  • acknowledge_garmin_source — Garmin brand attribution shown when data is first presented.

Where to get it

  • ChatGPT: search "Fitness AI Connector" in the Apps Directory (works with Free ChatGPT accounts via our Custom GPT as well)
  • Claude: add as a custom connector — MCP endpoint: https://garmin-mcp-nuqd.onrender.com/mcp
  • Details and setup guides: https://fmp.it.com/en/fitness-ai/

How it compares

There are several ways to connect Garmin data to AI assistants. An honest comparison:

Fitness AI Connector Self-hosted OSS (e.g. garmin_mcp) Hosted credential-based connectors
Garmin access Garmin Health API (official developer program) Unofficial (reverse-engineered) API Unofficial (reverse-engineered) API
Authentication OAuth on Garmin's page; no password shared Your Garmin email + password Your Garmin email + password stored by operator
Setup None (hosted) Local install (Python/Node) None (hosted)
Works on mobile / web chat Yes Desktop only (local process) Yes
Historical data From connection date onward (Garmin API policy) Full history Full history
Tool count 12 focused tools Up to 110+ tools Varies
Price Free tier; Basic $3/month Free (self-managed) Free
Continuity risk Contract-backed API Breaks when Garmin changes internal auth Breaks when Garmin changes internal auth

Self-hosted OSS is a great choice for developers who want maximum tool coverage and full local control. Fitness AI Connector is built for people who want a no-setup, no-password-sharing option that works in the ChatGPT and Claude apps, backed by the Garmin Health API.

Privacy & security

  • OAuth 2.0 with PKCE; Garmin credentials are never seen or stored by us
  • Data deletion on request with a 30-day recovery window; automated purge afterwards
  • Privacy policy: https://fmp.it.com/en/fitness-ai/privacy/ · Terms: https://fmp.it.com/en/fitness-ai/terms/

Support

  • Email: contact@fmp.it.com
  • Website: https://fmp.it.com

Connects to Garmin Connect™ through the Garmin Health API. Garmin, the Garmin logo, and Garmin Connect are trademarks of Garmin Ltd. or its subsidiaries. This project is not affiliated with, endorsed, or sponsored by Garmin.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选