Used for data models to structure requests and responses for the grocery search functionality.
Planned for future enhancement to provide caching for price data, though not currently implemented.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Grocery Search MCP Server search for protein bars at Trader Joe's"
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.
An MCP (Model Context Protocol) server that provides grocery price and nutritional information search capabilities. This server allows AI agents to search for food products, compare prices, and analyze nutritional content across different grocery stores.
Product Search: Search for grocery items by name across supported stores
Price Comparison: Get current pricing information for food products
Nutritional Analysis: Retrieve protein, calorie, and other macro information
Protein-per-Dollar Ranking: Automatically rank products by protein content per dollar spent
Store Support: Currently supports Trader Joe's (more stores coming soon)
Related MCP server: Instacart MCP Server
Clone the repository:
git clone <repository-url>
cd MCP_Food_SearchInstall dependencies:
pip install -r requirements.txtOr install in development mode:
pip install -e .Start the server using:
python -m grocery_search_mcp.serverOr using the script entry point:
grocery-search-mcpRun the test script to verify functionality:
python test_server.pyThe server provides one main tool:
GroceryPrices.searchSearch for grocery items with price and nutritional information.
Parameters:
query (required): Food or product name to search for
store (optional): Store to search, defaults to "trader_joes"
Example:
{
"query": "protein bar",
"store": "trader_joes"
}Response: Returns a formatted list of products with:
Product name and brand
Price and package size
Protein content and calories
Protein-per-dollar ratio
Nutritional information status
The server consists of several key components:
MCP Server (server.py): Main MCP protocol implementation
Data Models (models.py): Pydantic models for requests/responses
Scrapers (scraper.py): Web scraping logic for different stores
Nutrition Estimation: Basic nutritional information estimation
This initial version includes:
✅ Basic MCP server setup
✅ Trader Joe's product search (mock data for now)
✅ Nutritional estimation based on product names
✅ Protein-per-dollar calculation
✅ Error handling and logging
Real web scraping implementation
Integration with USDA FoodData Central API
Redis caching for price data
Additional store support (Safeway, Kroger, etc.)
Real-time inventory checking
Advanced nutritional analysis
This is a learning project. Feel free to submit issues and enhancement requests.
MIT License
This server cannot be deployed
Cached US grocery prices, age disclosed on every row - search, compare across banners, coverage.
Agent-native product catalog: 300M+ products, 150,000+ stores, deliver_to ranking.
AI-agent product catalog: search, lookup & purchase routing over verified merchant data.
Where to buy a whole grocery list today: local prices, per-unit and cross-store comparison.