
Healthy Pokes
A calorie tracking MCP server that processes food photos and text descriptions to automatically log nutrition data to Google Sheets. Integrates with Apple Health for fitness metrics and provides SMS interface for convenient meal logging.
README
Healthy Pokes
A calorie tracking MCP (Model Context Protocol) server that integrates meal logging with nutrition data and health metrics.
Features
- 📸 Process food photos and text descriptions using GPT-4o Vision
- 🥗 Automatic nutrition estimation via OpenNutrition MCP
- 📊 Google Sheets integration for personalized tracking
- 🏃 Apple Health integration for activity and weight data
- 📱 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 keys
Environment 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 # Optional
Usage
Running Locally
python server.py
The 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/
├── server.py # Main MCP server
├── tools/ # MCP tool implementations
│ ├── __init__.py
│ ├── google_sheets.py
│ ├── nutrition.py
│ ├── vision.py
│ └── messaging.py
├── utils/ # Helper functions
├── requirements.txt # Python dependencies
├── render.yaml # Render deployment config
└── .env.example # Environment template
Testing
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
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。