Which vendors are supported?
The README mentions Rami Levy and Keshet as available vendor names when starting the server.
@o-b-one
Basic information
An mcp server for groceries vendors
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"groceries": {
"command": "uv",
"args": [
"run",
"mcp-groceries-server",
"--vendor",
"<vendorName # rami-levy, keshet e.g>"
],
"env": {
"VENDOR_API_KEY": "<YOUR_API_TOKEN>",
"VENDOR_ACCOUNT_ID": "<VENDOR_ACCOUNT_ID>"
}
}
}
}`items`(list[CartItemScheam]): items to add to the cart
Updated cart
It is an MCP server that interfaces with grocery vendor APIs (such as Rami Levy and Keshet), enabling users to search for groceries and manage cart updates automatically. It is intended for developers building AI‑powered grocery assistants.
Obtain a vendor API key and account ID from the vendor’s website (e.g., from localStorage on the Rami Levy site). Set environment variables (VENDOR_API_KEY, VENDOR_ACCOUNT_ID) in a .env file or in the Claude Desktop configuration. Then run the server via uv run mcp-groceries-server --vendor <vendorName> or use the provided Docker image.
add_items_to_cart and search.The README mentions Rami Levy and Keshet as available vendor names when starting the server.
For Rami Levy, log in to the site, open developer tools (F12), and run the provided JavaScript snippet to extract `VENDOR_ACCOUNT_ID` and `VENDOR_API_KEY` from `localStorage`.
Two tools: `add_items_to_cart` (accepts a list of items and returns the updated cart) and `search` (accepts a search string and returns matching items).
The server uses `uv` (a Python package manager) and requires the `mcp-groceries-server` package. Docker is also supported for building a container.
All data comes directly from the vendor’s own API; no external databases are used. The server acts as a bridge to that API.

Model Context Protocol Servers

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
🚀 The fast, Pythonic way to build MCP servers and clients.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
不止于 CSS
Comments