Garmin Sailing MCP
Turns your Garmin watch into a sailing analytics tool by combining GPS data from Garmin Connect with historical weather data, providing insights like speed, VMG, wind conditions, and interactive maps.
README
Garmin Sailing MCP
An MCP server that turns your Garmin watch into a sailing analytics tool. Combines GPS data from Garmin Connect with historical weather from Open-Meteo to give you sailing-specific insights — all accessible through Claude.

What it does
| Tool | Description |
|---|---|
get_sailing_activities |
List your recent sailing sessions |
get_sailing_activity |
Detailed analysis: speed (knots), distance (nm), VMG, wind, tacks, point of sail |
get_sailing_map |
Interactive map with GPS trace colored by speed + wind overlay |
Sailing analysis includes
- Speed in knots, distance in nautical miles
- Wind conditions during your sail (speed, direction, gusts) via Open-Meteo
- VMG (Velocity Made Good) — how efficiently you sailed relative to wind
- Maneuver detection — tack and jibe count from heading changes
- Point of sail distribution — % time close hauled, beam reach, broad reach, running
- Storm indicators — precipitation, cloud cover, CAPE
- Heart rate stats
Architecture
graph TD
A[User] -->|activity_id| B[get_sailing_map]
B --> C[Garmin Connect API]
B --> D[Open-Meteo API]
C -->|track, speed, HR| E[Sailing Analyzer]
D -->|wind, rain, temp| E
E -->|JSON| F[Leaflet Map UI]
F --> G[Speed-colored trace]
F --> H[Wind arrow + stats]
Setup
1. Clone and install
git clone https://github.com/vinicius-saraiva/garmin-sailing-mcp.git
cd garmin-sailing-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e .
2. Authenticate with Garmin
python -m garmin_sailing setup
This will ask for your Garmin Connect email and password (+ MFA if enabled). Tokens are stored locally in ~/.garminconnect.
3. Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"garmin-sailing": {
"command": "/path/to/garmin-sailing-mcp/.venv/bin/python",
"args": ["-m", "garmin_sailing", "serve"],
"env": {
"PYTHONUNBUFFERED": "1"
}
}
}
}
Replace /path/to/garmin-sailing-mcp with the actual path where you cloned the repo.
Restart Claude Desktop and you're ready to sail!
Usage
Just talk to Claude:
- "How was my last sailing session?"
- "Show me the map of my latest sail"
- "Compare my last 5 sailing activities"
- "What were the wind conditions during my sail on March 7?"
Requirements
- Python 3.11+
- A Garmin watch that records sailing activities
- Claude Desktop (for the interactive map) or Claude Code
Credits
- garminconnect — Garmin Connect API client
- Open-Meteo — Free weather API (no key needed)
- FastMCP — MCP server framework
- Leaflet — Interactive maps
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。