Google Search MCP Server

Name: Google Search MCP Server
Author: ayush-rudani

@ayush-rudani

代码仓库

关于 Google Search MCP Server

An MCP server implementation that integrates with Google's Custom Search JSON API, providing web search capabilities.

#google-search #mcp-server #api-integration

基本信息

分类

搜索

许可证

MIT license

运行时

node

传输方式

stdio

发布者

ayush-rudani

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "google-search-mcp-server-ayush-rudani": {
      "command": "node",
      "args": [
        "dist/index.js"
      ]
    }
  }
}

工具

Execute Google searches with advanced filtering options

概览

What is Google Search MCP Server?

An MCP server implementation that integrates with Google's Custom Search JSON API, providing web search capabilities for use with MCP clients like Claude Desktop.

How to use Google Search MCP Server?

Obtain a Google API key and Custom Search Engine ID from the Google Cloud Console and Programmable Search Engine. Set the environment variables GOOGLE_API_KEY and GOOGLE_SEARCH_ENGINE_ID. Configure the server in claude_desktop_config.json with the full path to Node.js and the built index.js file. Alternatively, clone the repository, install dependencies with npm/pnpm, build, and run node dist/index.js.

Key features of Google Search MCP Server

Web search with comprehensive query options
Advanced filtering by date, language, and country
Safe search level control (off, medium, high)
Built-in rate limiting to prevent API quota exhaustion
Structured results with titles, URLs, and snippets

Use cases of Google Search MCP Server

Perform real-time web searches from within Claude Desktop
Retrieve current information for research and fact-checking
Filter search results by date to find recent content
Limit searches to a specific language or country
Automate web lookups as part of AI assistant workflows

FAQ from Google Search MCP Server

What dependencies are required to run this server?

Node.js is required. You also need a Google Cloud project with the Custom Search JSON API enabled and a Search Engine ID from Google's Programmable Search Engine.

How do I obtain the necessary API keys?

Create a Google Cloud project, enable the Custom Search JSON API, generate an API key from the Credentials section, and set up a search engine via Programmable Search Engine to get a Search Engine ID.

What is the default rate limit and can I change it?

The server enforces a rate limit of 10 requests per minute by default. You can adjust this value in the source code if needed.

How do I configure the server for Claude Desktop?

Add an entry to claude_desktop_config.json specifying the full path to Node.js as the command and the full path to the built index.js as an argument, along with the required environment variables.

What search options are available in the `google_search` tool?

The tool accepts a required query string and optional parameters: num_results (1-10, default

搜索分类下的更多 MCP 服务器

mcp-omnisearch

spences10

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

332