Liga o teu Garmin ao Claude em 3 passos (sem programar)

Um servidor MCP (Model Context Protocol) permite que o Claude leia os teus dados do Garmin Connect diretamente — sem exportar, sem copiar e colar. Instala-o como extensão do Claude Desktop em três passos e pergunta ao Claude o que quiseres sobre o teu treino, sono ou recuperação.
Day 102: Connect Your Garmin to Claude in 3 Steps
Previous Garmin School guides showed you how to export a ZIP file from Garmin Connect and hand it to Claude. That works, but it's a manual snapshot — you have to re-export every time you want fresh data. An MCP server removes that step entirely: it connects Claude directly to your Garmin account, so it can pull your latest activities, sleep, HRV, stress, and training data on demand, in every conversation, without you exporting anything.
What is MCP?
Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude connect to external data sources and tools. A "Garmin MCP server" is a small program that speaks MCP on one side and the Garmin Connect API on the other — Claude asks it a question, it fetches the answer from your Garmin account. This guide uses the free, open-source garmin_mcp project. No coding experience needed — every step below is copy-paste.
Step 1: Open a terminal
On Mac: Press Cmd + Space, type Terminal, and press Enter.
On Windows: Press the Windows key, type PowerShell, and press Enter.
Step 2: Install uv (a small required tool)
The Garmin MCP server runs through uv, a free tool that downloads and runs it for you — including Python itself, so you don't need to install Python separately. Paste the command for your system into the terminal you just opened and press Enter:
Mac:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Text will scroll by — that's normal. When it stops and shows a new cursor, it's done. You only ever need to do this once on this computer.
Step 3: Log in to Garmin, from the terminal
Still in the same terminal window, paste this and press Enter (the first run may take a minute, since it also downloads a small Python runtime automatically):
uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp-auth
It will ask for your Garmin email, password, and — if you have it enabled — your MFA code. Type each one and press Enter. This saves a secure login token on your computer, valid for about six months, so Claude will never have to ask you to log in again.
Step 4: Download the Garmin MCP extension
Go to the project's Releases page and download the latest garmin-mcp.dxt file, listed under "Assets".
Step 5: Install it in Claude Desktop
Open the Claude desktop app (download and install it first if you haven't already), then drag the garmin-mcp.dxt file you just downloaded straight onto the Claude Desktop window. You can also double-click the file, or go to Settings → Extensions → Install Extension and pick it manually.
Claude shows a short configuration screen for the extension, with optional fields like token path, email, and password. Because you already logged in during Step 3, leave every field empty and just confirm — Claude uses your saved login automatically.
Step 6: Restart Claude Desktop
Fully quit and reopen Claude Desktop, then start a new conversation. Your Garmin data — recent activities, sleep stages, HRV status, stress, Body Battery, training load and readiness, VO2 max trends, and more — is now available to Claude directly, with no export and no copy-pasting.
If something goes wrong
- If Claude says it can't find
uvx, typewhich uvx(Mac) into the terminal, copy the path it prints, and paste that full path into the extension's "command" field instead ofuvx. - Your login token lasts about six months. If Claude suddenly stops seeing your data, just repeat Step 3.
Try it: find patterns in your sleep
Here's a prompt that puts the connection to work immediately. It cross-references your sleep with your daytime training and stress — not just a list of sleep scores — and asks for a proper Word document back:
Analyze my last 14 days of sleep data alongside my daytime activity, training, and stress data to find patterns — not just a summary of sleep scores. Produce the result as a clean, well-formatted document (Word doc), not a chat reply. Pull for each of the last 14 days: - Sleep score, total sleep time, sleep stages (deep/light/REM/awake), overnight HRV, resting HR - Bedtime and wake time (consistency/variability) - That day's training load, activity type, intensity, and time of day it happened - Daytime stress levels and Body Battery (start, end, charge/drain pattern) - Any logged alcohol, caffeine, or late meals if available Then do two things: 1. Pattern analysis — find the 2-3 strongest correlations across the 14 days (e.g. training timing vs. sleep score, stress vs. deep sleep %, bedtime consistency vs. sleep quality), each backed by specific data points. 2. Best night / worst night deep dive — identify my single best and single worst sleep night in this period. For each one, reconstruct that full day: what I did, when, training load, stress, Body Battery trend, bedtime. Then explain why that night likely turned out the way it did, connecting the dots between the day's data and the sleep outcome — don't just restate the numbers, explain the mechanism (e.g. "late intense training kept HR elevated into the evening, delaying the drop needed for deep sleep"). Structure the document as: - Summary (3-4 sentences, plain language) - 14-day data table (date, sleep score, key metrics, notable daytime factors) - Pattern analysis section - Best night breakdown - Worst night breakdown - 2-3 practical adjustments to test, based on the above Keep language direct and practical, no fluff.
Give it a minute to pull the data and write it up. Because Claude reads your Garmin account directly, you can ask a follow-up question straight after — "what about the two weeks before that?" — without exporting anything again.
Juntar-se à Garmin School
Deixe seu e-mail para acessar a Garmin School e receber atualizações sobre novos vídeos e apps.




