Israel Grocery MCP
Enables cross-store price comparison and recipe-driven cart automation for Israeli grocery stores Shufersal and Tiv Taam, with an extensible architecture for additional stores.
README
Israel Grocery MCP
Unified Model Context Protocol (MCP) server for Israeli grocery shopping — Shufersal + Tiv Taam with cross-store price comparison, recipe-driven cart automation, and an extensible plugin architecture for future stores.
Features
- Cross-store search — search both Shufersal and Tiv Taam simultaneously
- Price comparison — see side-by-side pricing for any product or full recipe
- Smart recipe shopping — parse any recipe, find the best deals across stores, and add items to the cheapest cart automatically
- Split-cart recommendations — buy each ingredient from wherever it's cheapest and see your total savings
- Preference system — set a preferred store, shopping strategy (cheapest / preferred / quality), organic preference, brand blacklisting, and more
- Diagnostics tool —
diagnose()surfaces HTTP errors, response shapes, and session state
Setup
1. Install uv
curl -Ls https://astral.sh/uv/install.sh | sh
2. Install dependencies
cd israelgrocery
uv sync
3. Install Playwright (required for Shufersal browser login)
uv run playwright install chromium
4. Configure environment (optional)
cp .env.example .env
# Edit .env as needed
Running the server
uv run israelgrocery-mcp
Claude Desktop configuration
{
"mcpServers": {
"israelgrocery": {
"command": "uv",
"args": ["--directory", "/path/to/israelgrocery", "run", "israelgrocery-mcp"]
}
}
}
Available MCP Tools
| Tool | Description |
|---|---|
login_status() |
Show login status for all stores |
login_tivtaam(email, password) |
Log in to Tiv Taam |
login_shufersal() |
Open browser for Shufersal login |
check_login(store_id?) |
Live session validation |
set_preferences(...) |
Shopping preferences |
search_products(query, stores?) |
Search across stores |
compare_prices(query) |
Price comparison for an item |
show_cart(store_id?) |
View cart(s) |
add_to_cart(store_id, product_id, qty) |
Add to a specific cart |
plan_recipe_ingredients(recipe_text) |
Parse recipe ingredients |
compare_recipe(recipe_text) |
Full recipe cost comparison |
add_recipe_to_cart(recipe_text, ...) |
Automated recipe shopping |
diagnose(store_id?) |
Debug API connections |
Example prompts for Claude
- "Compare prices for eggs and milk across both stores"
- "I want to make shakshuka — find all the ingredients and tell me where to buy them cheapest"
- "Add this pasta recipe to my Tiv Taam cart: [paste recipe]"
- "Buy each ingredient from wherever it's cheapest and show me the savings"
- "Search for chicken breast on both stores"
Shopping strategies
| Strategy | Behaviour |
|---|---|
cheapest (default) |
Each item is bought from whichever store has the lower price |
preferred_store |
Always use your set preferred store unless it has no match |
quality |
Prefer the highest-confidence product match regardless of price |
Adding a new store
- Create
src/stores/mystore.pyimplementingBaseStore - Register it in
src/stores/__init__.py→build_registry() - Add config in
src/config.py - Done — all existing tools automatically include the new store
Running tests
uv run pytest tests/ -v
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.