About 🧠 SmartMenu MCP Server
SmartMenu MCP Server connects LLMs to structured restaurant menu data through a backend API. It exposes menu resources and tools for searching menus, filtering dishes and retrieving item details, supporting grounded recommendations.
Key features
- 01Expose structured menus as resources
- 02Find menus by name or ID
- 03Filter dishes by tags, price or restrictions
- 04List menus and available tags
- 05Retrieve full menu-item details
Use cases
- 01Answering questions about restaurant menus
- 02Finding dishes by dietary limits or budget
- 03Getting details for a specific menu item
MCP support
It exposes structured menus as MCP resources and provides tools for menu lookup, dish filtering, listing menus and tags, and retrieving item details.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README🧠 SmartMenu MCP Server
This is the Model Context Protocol (MCP) server for SmartMenu, an AI-powered assistant that helps customers interact with restaurant menus through natural language.
The MCP server acts as a bridge between large language models (LLMs) like GPT-4 and your structured menu data. It exposes tools and resources that allow the model to reason over real menus and provide grounded, context-aware recommendations.
📦 Features
- Exposes structured menus as resources to the LLM
- Provides a rich set of tools for:
- Finding menus by name or ID
- Filtering dishes by dietary tags, price, or restrictions
- Listing all available menus and tags
- Returning full details for specific menu items
- Connects to a real backend API via REST
- Built with the official
@modelcontextprotocol/sdk
🧱 Architecture
Frontend (React) ←→ Backend (Express + DB)
↓
[SmartMenu MCP]
↓
LLM (ChatGPT, Claude, etc.)
🚀 Getting Started
- Clone the project:
git clone https://github.com/logeshselvam/mcp-server.git
cd mcp-server
- Install dependencies:
npm install
- Run the inspector:
npm run inspect
- Test with Cursor: Open Cursor setting and add the following:
"smart-menu": {
"command": "npm",
"args": [
"--silent",
"--prefix",
// your project path, you can find it using `pwd` command
"run",
"dev"
]
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.