Garmin MCP Server for Poke

Garmin MCP Server for Poke

Exposes over 90 Garmin Connect tools for tracking activities, health metrics, and training data through the Model Context Protocol. It is optimized for Poke compatibility and supports deployment to Render via HTTP.

Category
Visit Server

README

Garmin MCP Server for Poke

A Poke-compatible MCP server exposing 90+ Garmin Connect tools over HTTP via FastMCP. Deployable to Render.

Built on top of Taxuspt/garmin_mcp and InteractionCo/mcp-server-template.

Deploy to Render

Setup

1. Generate OAuth Tokens

Garmin accounts with MFA require local token generation:

pip install garminconnect garth
python scripts/generate_tokens.py

This will prompt for your Garmin email, password, and MFA code, then output a base64 token string.

2. Deploy to Render

Option 1: One-Click Deploy

Click the "Deploy to Render" button above, then set GARMINTOKENS_BASE64 to the token string from step 1.

Option 2: Manual Deployment

  1. Fork this repository
  2. Connect your GitHub account to Render
  3. Create a new Web Service on Render
  4. Connect your forked repository
  5. Render will automatically detect the render.yaml configuration
  6. Set GARMINTOKENS_BASE64 in environment variables

Your server will be available at https://your-service-name.onrender.com/mcp

3. Connect Poke

Add your Render URL to Poke at poke.com/settings/connections:

https://your-service-name.onrender.com/mcp

Local Development

pip install -r requirements.txt
cp .env.example .env
# Edit .env and set GARMINTOKENS_BASE64
python src/server.py

Test with MCP Inspector:

npx @modelcontextprotocol/inspector

Open http://localhost:3000 and connect to http://localhost:8000/mcp using "Streamable HTTP" transport.

Token Refresh

Tokens last approximately 6 months. When they expire, re-run generate_tokens.py and update the Render env var.

Tool Categories

Category Tools Examples
Activity Management 14 Activities by date, splits, weather, HR zones, gear
Health & Wellness 28 Stats, sleep, stress, body battery, HRV, SpO2, steps
Training 10 Training status, endurance score, hill score, lactate threshold
User Profile 4 Profile info, settings, unit system
Devices 7 Device list, settings, alarms, solar data
Gear Management 3 Gear inventory, add/remove gear from activities
Weight Management 5 Weigh-ins, add/delete measurements
Challenges 10 Goals, badges, challenges, race predictions, PRs
Workouts 7 Workout library, scheduling, training plans, upload
Data Management 3 Body composition, blood pressure, hydration
Women's Health 3 Pregnancy, menstrual cycle tracking
Workout Templates 5 Resources with workout JSON templates

Attribution

Built on top of:

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

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.

Official
Featured
Python
graphlit-mcp-server

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.

Official
Featured
TypeScript
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured