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
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。