Rami Levy MCP server

The MCP Server for Rami Levy Online Grocery Store API enables integration between Rami Levy's e-commerce platform and MCP-enabled Large Language Models. This server acts as a bridge, allowing AI models to search the store's catalog, manage shopping carts, and facilitate checkout processes.

Available Tools

Search Items

• Search for products in Rami Levy's catalog
• Inputs:
  • q (string): Search query
  • store (string, optional): Store identifier (default: "331")
  • aggs (number, optional): Aggregation flag (default: 1)
• Returns: Array of products with name, price, image URL, and ID

Add to Cart

• Add one or more items to the shopping cart
• Inputs:
  • store (string): Store identifier (e.g., "331")
  • items (array): List of items to add, each containing:
    • id (number): Product identifier
    • quantity (number): Quantity to add (minimum: 1)
• Returns: Updated cart contents with prices and discounts

Remove from Cart

• Remove items from the cart by providing an updated list of items to keep
• Inputs:
  • store (string): Store identifier
  • items (array): Updated list of items to keep in cart
• Returns: Updated cart contents

Update Quantity

• Update the quantity of an item in the cart
• Inputs:
  • store (string): Store identifier
  • id (number): Product identifier
  • newQuantity (number): New quantity for the product (minimum: 1)
• Returns: Updated cart contents

Available Resources

Checkout URL

• Resource: rami-levy://checkout
• Gets the URL for the Rami Levy checkout page
• Returns: Checkout page URL

Installation and Setup

Authentication Setup

This MCP server requires authentication tokens from an active Rami Levy session:

1. Log in to Rami Levy's website
2. Open your browser's developer tools (F12)
3. Go to the Network tab
4. Make any request (e.g., search for a product)
5. From the request headers, extract:
   • RAMI_LEVY_API_KEY: The token after "Bearer" in the Authorization header
   • ECOM_TOKEN: The full ecomtoken header value
   • COOKIE: The complete cookie header value

Environment Configuration

Create a .env file with the following variables:

RAMI_LEVY_API_KEY=your_api_key_here
ECOM_TOKEN=your_ecom_token_here
COOKIE=your_cookie_string_here

Using with Claude Desktop

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "rami-levy": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-rami-levy"
      ],
      "env": {
        "RAMI_LEVY_API_KEY": "<YOUR_API_KEY>",
        "ECOM_TOKEN": "<YOUR_ECOM_TOKEN>",
        "COOKIE": "<YOUR_COOKIE>"
      }
    }
  }
}

Starting the Server

To start the server directly:

npm install
npm run build
npm start

Security Considerations

⚠️ Important:

• The authentication tokens provide full access to your Rami Levy account
• Keep tokens secure and never commit them to version control
• Tokens expire periodically and will need to be refreshed
• This implementation is intended as a proof of concept

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "rami-levy" '{"command":"npx","args":["-y","@modelcontextprotocol/server-rami-levy"],"env":{"RAMI_LEVY_API_KEY":"<YOUR_API_KEY>","ECOM_TOKEN":"<YOUR_ECOM_TOKEN>","COOKIE":"<YOUR_COOKIE>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "rami-levy": {
            "command": "npx",
            "args": [
                "-y",
                "@modelcontextprotocol/server-rami-levy"
            ],
            "env": {
                "RAMI_LEVY_API_KEY": "<YOUR_API_KEY>",
                "ECOM_TOKEN": "<YOUR_ECOM_TOKEN>",
                "COOKIE": "<YOUR_COOKIE>"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "rami-levy": {
            "command": "npx",
            "args": [
                "-y",
                "@modelcontextprotocol/server-rami-levy"
            ],
            "env": {
                "RAMI_LEVY_API_KEY": "<YOUR_API_KEY>",
                "ECOM_TOKEN": "<YOUR_ECOM_TOKEN>",
                "COOKIE": "<YOUR_COOKIE>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect