Which integrations are available for this server?

Provides tools for interacting with Garmin Connect, enabling AI agents to retrieve health metrics, activities, sleep data, HRV trends, download FIT files, and query the local relational database.

How do I use GarminSynapse?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@GarminSynapse Show my sleep stages and HRV status for today." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

GarminSynapse

by kaivyy

Overview Schema Related Servers Score Discussions

Python

Local

⚡ GarminSynapse

Unified Health Engine, Relational Database, Native MCP Server & Web Dashboard for Garmin Connect.

Python 3.9+ FastAPI MCP SDK 2.0 SQLite License: MIT Code Style: Black

Bridge your Garmin training data, health metrics, and raw .FIT files directly to AI Agents (Claude, Cursor, AGY) and modern web clients.

Features • Architecture • Quick Start • MCP Guide • REST API • License

🌟 Key Features

Related MCP server: Garmin Workouts MCP Server

🏗️ System Architecture

flowchart TD
    subgraph Cloud["Garmin Connect Cloud"]
        GC["Garmin API Endpoints (180+ Methods)"]
    end

    subgraph Auth["Dual-Engine Auth Core"]
        CFFI["curl_cffi (Chrome TLS Impersonation)"]
        PW["Playwright Chromium Fallback"]
    end

    subgraph Storage["Storage & ETL Engine"]
        EXT["GarminExtractor"]
        PROC["GarminProcessor"]
        DB[("SQLite Database\n(40+ Relational Tables)")]
    end

    subgraph Access["Interfaces"]
        MCP["MCPServer (SDK 2.0)\n(STDIO & SSE)"]
        REST["FastAPI REST API\n(Port 6060)"]
        SPA["Web Dashboard SPA\n(Dark/Light Mode)"]
    end

    subgraph Clients["Clients"]
        AI["AI Agents\n(Claude, Cursor, AGY)"]
        User["User Browser / Tailscale"]
    end

    GC --> Auth
    Auth --> EXT
    EXT --> PROC
    PROC --> DB
    DB --> MCP
    DB --> REST
    REST --> SPA
    MCP --> AI
    SPA --> User

⚡ Quick Start

TIP

Zero-Friction Install: install.sh automatically checks & installs all prerequisites (Python ≥ 3.9, pip, git, system libs, Playwright browser, all 13 Python packages). Users never need to install anything manually.

Prerequisites (auto-handled by `install.sh`)

Requirement	Version	Notes
Python	≥ 3.9	Script checks and errors if missing
pip	Any	Auto-installed via apt/dnf/pacman/brew
git	Any	Auto-installed if missing
System libs	libnss3, libgbm1, etc.	Auto-installed for Playwright on Debian/Ubuntu

Installation

# 1. Clone Repository
git clone https://github.com/kaivyy/garminsynapse.git
cd garminsynapse

# 2. One-Click Setup (checks & installs everything)
chmod +x install.sh
./install.sh

# 3. Start Web Dashboard (Port 6060)
garminsynapse start-server
# or: python3 -m garminsynapse.cli start-server

Open your browser at http://localhost:6060 or via Tailscale IP http://<IP-Tailscale-Server>:6060.

What `install.sh` does

✅ Checks Python ≥ 3.9, pip, git — auto-installs if missing
✅ Installs system libraries for Playwright (Debian/Ubuntu)
✅ Runs pip install -e .[dev] (all 13 dependencies from pyproject.toml)
✅ Installs Playwright Chromium browser binary
✅ Creates garmin_files/ working directories and ~/.garminsynapse/ config
✅ Validates installation by importing all modules and testing the web server

NOTE

Norequirements.txt needed — all dependencies are declared in pyproject.toml using modern PEP 621 standards.

📦 Dependencies

All installed automatically via pyproject.toml:

Package	Purpose
`fastapi` + `uvicorn`	REST API server & web dashboard
`click`	CLI interface (`garminsynapse` command)
`sqlalchemy`	SQLite ORM with 40+ table schema
`curl_cffi`	Primary auth via Chrome TLS fingerprint
`playwright`	Fallback auth via headless Chromium
`garminconnect`	Garmin Connect API client wrapper
`mcp` (v2.0)	Model Context Protocol server SDK
`fitdecode`	Binary `.FIT` file parser
`defusedxml`	Safe XML/TCX parsing
`requests`	HTTP utilities
`pydantic`	Data validation (via FastAPI)
`pytest`	Test suite (dev dependency)

🤖 MCP Integration Guide

Connect GarminSynapse to your favorite AI Assistant in seconds.

Claude Desktop Setup

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "garminsynapse": {
      "command": "python3",
      "args": ["-m", "garminsynapse.cli", "mcp"],
      "env": {
        "PYTHONPATH": "${workspaceFolder}/src"
      }
    }
  }
}

Cursor & AGY Setup

In Editor Settings -> Model Context Protocol (MCP) -> Add New Command:

Name: garminsynapse
Command: python3 -m garminsynapse.cli mcp

🛠️ MCP Tools Reference (20 Native AI Tools)

Tool Name	Parameters	Description
`garmin_status`	None	Check auth, database, and MCP system status
`garmin_login`	`email`, `password`	Authenticate with Garmin Connect
`get_garmin_devices`	None	Get registered watch model names, serial numbers, unit IDs, and firmware
`get_live_metrics`	None	Get live point-in-time metrics (Body Battery %, charged/drained, Stress, Steps, Nap)
`garmin_sync`	`days` (default 7)	Extract recent Garmin metrics to SQLite database
`get_daily_summary`	`date_str` (`YYYY-MM-DD`)	Get daily steps, RHR, stress, body battery, calories, distance
`get_sleep_analysis`	`date_str` (`YYYY-MM-DD`)	Get sleep stages, sleep score, and daytime nap intervals
`get_training_readiness`	`date_str` (optional)	Get Training Readiness score (0–100) and recovery factors
`get_race_predictions`	None	Get race time predictions for 5K, 10K, Half Marathon, and Marathon
`get_earned_badges`	None	Get user's earned Garmin Connect achievement badges
`get_hrv_trends`	`date_str` (optional)	Get HRV status, weekly baseline, and nightly averages
`get_respiration_data`	`date_str` (optional)	Get waking and sleep respiration rates (brpm)
`get_spo2_data`	`date_str` (optional)	Get blood oxygen saturation (SpO2 / Pulse Ox %) daily time-series
`get_hydration_data`	`date_str` (optional)	Get daily water intake and hydration logs
`get_fitness_age`	None	Get calculated Fitness Age vs chronological age
`get_user_profile`	None	Get user social and biometric profile (weight, height, gender, VO2 Max)
`list_activities`	`limit` (default 20)	List recent workouts (distance, duration, HR, calories)
`get_activity_details`	`activity_id`	Get detailed time-series metrics & map polyline
`download_fit_file`	`activity_id`	Download raw binary `.FIT` file to local storage
`query_garmin_db`	`sql_query`	Execute safe `SELECT` query on SQLite DB (40+ tables)

📡 REST API Endpoints (Port 6060)

Method	Endpoint	Description
`GET`	`/api/v1/status`	System health & authentication status
`POST`	`/api/v1/auth/login`	Authenticate Garmin Connect account
`POST`	`/api/v1/auth/logout`	Clear active token session
`GET`	`/api/v1/devices`	Connected Garmin watch info with 6-hour cache
`GET`	`/api/v1/live`	Live real-time biometric readings (Body Battery, Stress, Steps, Nap)
`GET`	`/api/v1/summary`	Health gauges (Steps, HR, Sleep, Battery, HRV, SpO2, Respiration)
`GET`	`/api/v1/readiness`	Training Readiness score & recovery factor breakdown
`GET`	`/api/v1/predictions`	Race time predictions (5K, 10K, Half Marathon, Marathon)
`GET`	`/api/v1/badges`	User's earned Garmin Connect achievement badges
`GET`	`/api/v1/profile`	User social profile & biometric parameters
`GET`	`/api/v1/activities`	List recent logged workouts with date filters
`GET`	`/api/v1/activity/{id}`	Single activity full details
`POST`	`/api/v1/sync`	Trigger manual data extraction (with 5-minute cooldown)

🖥️ CLI Commands

# Start web dashboard
garminsynapse start-server [--host 0.0.0.0] [--port 6060]

# Sync Garmin data
garminsynapse sync --email you@mail.com --password yourpass [--days 7]

# Start MCP server (for AI agents)
garminsynapse mcp

# Downsample raw 1-second time-series metrics older than 30 days
garminsynapse downsample --days-keep-raw 30

# Prune historical activities older than 1 year
garminsynapse prune --days-keep 365

🧹 Database Maintenance

NOTE

Keep disk usage optimal by downsampling high-frequency 1-second metrics.

# Downsample raw 1-second time-series metrics older than 30 days
garminsynapse downsample --days-keep-raw 30

# Prune historical activities older than 1 year
garminsynapse prune --days-keep 365

🧪 Running Tests

# Run full test suite
PYTHONPATH=src pytest tests/ -v

# Run specific module tests
PYTHONPATH=src pytest tests/test_db.py -v
PYTHONPATH=src pytest tests/test_mcp.py -v

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

This server cannot be installed

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

license - not found

Not graded

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

2dRelease cycle

8Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

GC-MCP
Health & Wellness Fitness Tracking
macakdev
F
license
Not graded
quality
B
maintenance
Enables AI assistants to access and query Garmin Connect health and fitness data, including sleep, HRV, training load, and activities, with an optional coaching plugin for personalized training plans.
Updated 21 days ago (2026-08-10 06:40 UTC)
0
4
Garmin Workouts MCP Server
Health & Wellness Fitness Tracking
brunosantos
A
license
Not graded
quality
D
maintenance
Enables AI agents to access Garmin Connect activities, workouts, and workout templates for querying and creating workout plans.
Updated 5 months ago (2026-04-03 21:14 UTC)
5
MIT
garmin-givemydata
Health & Wellness Fitness Tracking
nrvim
A
license
Not graded
quality
A
maintenance
Downloads all your Garmin health and fitness data into a local SQLite database and exposes 45 MCP tools for AI analysis, enabling assistants to query sleep, training load, HRV, and more.
Updated 8 days ago (2026-08-22 18:43 UTC)
144
AGPL 3.0
garmin-mcp
Health & Wellness Fitness Tracking
shawnduggan
A
license
Not graded
quality
D
maintenance
Enables AI assistants to query live Garmin Connect health and fitness data, including daily metrics, activities, sleep analysis, and trends via natural language.
Updated 8 months ago (2026-01-04 23:36 UTC)
MIT

View all related MCP servers

Related MCP Connectors

Fitness AI Connector
Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.
Garmin — MissingMCP
Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.
Wellness Project
63 tools for Apple Health, Fitbit, Oura & Health Connect data in Claude, ChatGPT, Grok & Mistral.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kaivyy/garminsynapse'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

⚡ GarminSynapse

🌟 Key Features

🏗️ System Architecture

⚡ Quick Start

Prerequisites (auto-handled by install.sh)

Installation

What install.sh does

📦 Dependencies

🤖 MCP Integration Guide

Claude Desktop Setup

Cursor & AGY Setup

🛠️ MCP Tools Reference (20 Native AI Tools)

📡 REST API Endpoints (Port 6060)

🖥️ CLI Commands

🧹 Database Maintenance

🧪 Running Tests

📄 License

Maintenance

Resources

Looking for Admin?

Related MCP Servers

GC-MCP

Garmin Workouts MCP Server

garmin-givemydata

garmin-mcp

Related MCP Connectors

Latest Blog Posts

MCP directory API

Prerequisites (auto-handled by `install.sh`)

What `install.sh` does