Healthy Pokes
Integrates with Apple Health to retrieve fitness metrics, activity data, and weight measurements for health tracking
Provides persistent storage for user meal logging and nutrition tracking data through Google Sheets integration
Uses GPT-4o Vision to process food photos and text descriptions for automatic meal identification and logging
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Healthy Pokes
A calorie tracking MCP (Model Context Protocol) server that integrates meal logging with nutrition data and health metrics.
Features
πΈ Process food photos and text descriptions using GPT-4o Vision
π₯ Automatic nutrition estimation via OpenNutrition MCP
π Google Sheets integration for personalized tracking
π Apple Health integration for activity and weight data
π± SMS interface via Poke platform
Architecture
This MCP server acts as a bridge between multiple services:
OpenAI GPT-4o: Extracts food items from photos/text
OpenNutrition MCP: Provides nutrition data
Google Sheets: Stores user data persistently
Apple Health MCP: Retrieves fitness metrics
Poke Platform: Handles messaging interface
Setup
Prerequisites
Python 3.9+
Google Cloud Project with Sheets & Drive APIs enabled
OpenAI API key
Poke API key
Installation
# Clone the repository
git clone https://github.com/mattattacks/healthy-pokes.git
cd healthy-pokes
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Set up environment variables
cp .env.example .env
# Edit .env with your API keysEnvironment Variables
Create a .env file with:
OPENAI_API_KEY=your_openai_key
POKE_API_KEY=your_poke_key
GOOGLE_SERVICE_ACCOUNT_JSON={"type":"service_account"...}
HEALTH_DATA_DIR=/path/to/health/exports # OptionalUsage
Running Locally
python server.pyThe MCP server will be available at http://localhost:8000/mcp
Deploying to Render
This project includes a render.yaml for easy deployment to Render.
MCP Tools
connect_user(email)- Set up Google Sheet for useringest_image(image_url)- Process food photoparse_text(text)- Process text descriptionestimate_from_items(items)- Get nutrition datalog_rows(rows)- Save to Google Sheettoday_total()- Calculate daily intakehealth_summary()- Get Apple Health metricssend_message(text)- Reply via Poke
Development
Project Structure
healthy-pokes/
βββ server.py # Main MCP server
βββ tools/ # MCP tool implementations
β βββ __init__.py
β βββ google_sheets.py
β βββ nutrition.py
β βββ vision.py
β βββ messaging.py
βββ utils/ # Helper functions
βββ requirements.txt # Python dependencies
βββ render.yaml # Render deployment config
βββ .env.example # Environment templateTesting
pytest tests/Contributing
Pull requests are welcome! Please ensure all tests pass and follow the existing code style.
License
MIT
Acknowledgments
Built for the HackMIT Poke Challenge
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Food logging, nutrition summaries, and meal photo calorie and macro estimates.
Calorie and macro diary your AI fills in: log meals from text or photos, refine later, track goals.
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
AI-powered calorie tracking with photo recognition, barcode scanning, and voice logging