google_restaurant_mcp_server by LottaLai - MCP Server

Google Restaurant MCP Server

A fastmcp-based Model Context Protocol (MCP) server for Google Restaurant search and information.

Overview

This project provides a MCP server built with the fastmcp framework. It exposes tools, resources, and prompts that can be used by MCP clients like Claude Desktop to search and get information about restaurants via Google Maps API.

Features

Tools: Execute functions like add and multiply
Resources: Access dynamic content like personalized greetings
Prompts: Generate contextual prompts for various interactions
Google Maps Integration: Search for restaurants and get detailed information (coming soon)

Installation

Prerequisites

Python 3.10 or higher
uv package manager (recommended)

Setup

Clone or navigate to the project directory:

cd /Users/lotta/Documents/nibble_pixie_project/nibble_pixie_mcp_server

Install dependencies using uv:

uv sync

Or with pip:

pip install -e .

Usage

Running the Server

STDIO Transport (Default)

For local development and testing with MCP Inspector:

Configuration

You can configure the server using environment variables:

GOOGLE_MAPS_API_KEY: Your Google Maps API key for restaurant search functionality

Usage

Using stdio transport (default)

google-restaurant-server

Or directly with Python:

python src/google_restaurant_mcp_server/server.py

SSE Transport

For Server-Sent Events transport:

uv run google-restaurant-server --transport sse --host 127.0.0.1 --port 8000

Streamable HTTP Transport

For Streamable HTTP transport (recommended for production):

uv run google-restaurant-server --transport streamable-http --host 127.0.0.1 --port 8000

Testing with MCP Inspector

Test your server using the MCP Inspector:

npx @modelcontextprotocol/inspector uv run google-restaurant-server

Or with uv:

uv run mcp dev src/google_restaurant_mcp_server/server.py

Claude Desktop Integration

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "google-restaurant": {
      "command": "/path/to/your/.venv/bin/google-restaurant-server",
      "args": [],
      "env": {
        "GOOGLE_MAPS_API_KEY": "your-google-maps-api-key-here"
      }
    }
  }
}

Note: You need a valid Google Maps API key to use the restaurant search functionality.

Available Tools

Math Tools

All math tools are organized in the tools/math/ module.

`add`

Add two numbers together.

Parameters:

a (int): First number
b (int): Second number

Returns: Sum of the two numbers

`subtract`

Subtract two numbers.

Parameters:

a (int): Number to subtract from
b (int): Number to subtract

Returns: Difference of the two numbers

`multiply`

Multiply two numbers together.

Parameters:

x (int): First number
y (int): Second number

Returns: Product of the two numbers

`divide`

Divide two numbers.

Parameters:

a (float): Dividend
b (float): Divisor

Returns: Quotient of the two numbers

Available Resources

`greeting://{name}`

Get a personalized greeting.

Template Variables:

name: The name to greet

Available Prompts

`greet_user`

Generate a greeting prompt.

Arguments:

name (str): The name of the person to greet
style (str, optional): The style of greeting (friendly, formal, casual). Default: "friendly"

Development

Project Structure

google_restaurant_mcp_server/
├── .github/
│   └── copilot-instructions.md  # GitHub Copilot configuration
├── src/
│   └── google_restaurant_mcp_server/
│       ├── __init__.py          # Package initialization
│       ├── server.py            # Main server implementation
│       └── tools/               # Modular tools directory
│           ├── __init__.py
│           └── math/            # Math tools module
│               └── __init__.py
├── pyproject.toml               # Project configuration
├── README.md                    # This file
├── STRUCTURE.md                 # Project structure guide
└── EXAMPLES.md                  # Usage examples

Adding New Features

Adding a Tool

Tools are organized by category in the tools/ directory. See for detailed instructions.

Quick example:

Create a new module: tools/your_category/__init__.py
Implement the tool function
Register it in server.py:

from .tools import your_category

@mcp.tool()
def your_tool(param: str) -> str:
    """Tool description."""
    return your_category.your_tool(param)

Adding a Resource

@mcp.resource("your-resource://{param}")
def your_resource(param: str) -> str:
    """Resource description."""
    # Your implementation
    return content

Adding a Prompt

@mcp.prompt()
def your_prompt(param: str) -> str:
    """Prompt description."""
    # Your implementation
    return prompt_text

Configuration Options

Command Line Options

--transport: Transport protocol (stdio, sse, streamable-http). Default: stdio
--host: Host to bind to for HTTP transports. Default: 127.0.0.1
--port: Port to bind to for HTTP transports. Default: 8000
--log-level: Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL). Default: INFO

LottaLai/google_restaurant_mcp_server