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
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.