Google Search MCP Server

This project is a Model Context Protocol (MCP) server that provides Google Search API functionality to an AI assistant.

overview

The Google Search MCP Server is a tool that allows your AI Assistant to perform web searches using the Google Search API. It uses Gradio and MCP to provide the interface between your AI Assistant and the Google Search API.

Related MCP server: Scrapeless MCP Server

function

• Search the web with the Google Search API

• Returning search results in JSON format

• Get up to 20 search results

Prerequisites

• Python 3.12 or higher

• Google Custom Search Engine ID

• Google API Key

install

1. Clone the repository:

git clone https://github.com/yourusername/google-search-mcp-server.git
cd google-search-mcp-server

2. Install the dependencies:

pip install -e .

3. Set the environment variables:

Copy the .env.sample file to .env and add the necessary API keys:

cp .env.sample .env

Edit the .env file and set the following values:

GOOGLE_CSE_ID=あなたのGoogleカスタム検索エンジンID
GOOGLE_API_KEY=あなたのGoogleAPIキー

How to use

To start the server:

python app.py

This will start the Gradio interface and act as an MCP server.

Integration with MCP

This server is integrated with your AI assistant using the Model Context Protocol (MCP), and allows your AI assistant to access Google search functionality through the server.

API Reference

perform_web_search

perform_web_search(query: str, num_results: int = 10)

Parameters :

• query (str): The search query (max 400 characters, 50 words)

• num_results (int): Number of results (1-20, default 10).

Returns :

• str : Search results in JSON format