Google Search Engine MCP Server

Google Search Engine MCP Server

Enables Google search queries and webpage content extraction through an MCP server deployed on Cloudflare Workers. Supports single and batch webpage content extraction with integrated OAuth authentication.

Category
访问服务器

README

Google Search Engine MCP Server

An MCP (Model Context Protocol) server based on Cloudflare Workers, providing Google search and webpage content extraction functionality with integrated OAuth login.

Local Development

# Clone the repository
git clone https://github.com/your-username/google-search-engine-mcp-server.git

# Install dependencies
cd google-search-engine-mcp-server
npm install

# Run locally
npm run dev

Visit http://localhost:8787/ to check the server status

Connect to MCP Inspector Testing Tool

Use the MCP Inspector to explore and test the API:

  • Run npm run inspector or npx @modelcontextprotocol/inspector
  • In the Inspector interface, set the transport type to SSE, URL to http://localhost:8787/sse, and click "Connect"
  • Enter any email and password in the mock login interface
  • After logging in, you can view and call all available tools

<div align="center"> <img src="img/mcp-inspector-sse-config.png" alt="MCP Inspector Configuration Interface" width="600"/> </div>

Available Tools

This server provides the following tools:

  1. google_search - Perform Google searches and return results
  2. extract_webpage_content - Extract webpage content and convert it to readable text
  3. batch_extract_webpage_content - Batch extract content from multiple webpages

Connect to Claude Desktop

To connect Claude to your local MCP server:

  1. Follow the Anthropic Quick Start Guide
  2. In Claude Desktop, go to Settings > Developer > Edit Config
  3. Replace the existing content with the following configuration:
{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8787/sse"
      ]
    }
  }
}

After launching Claude, a browser window will open allowing you to log in. You can see available tools in the bottom right corner. With appropriate prompts, Claude will call the corresponding tools.

<div align="center"> <img src="img/available-tools.png" alt="Click the hammer icon to display the list of available tools" width="600"/> </div>

Deploy to Cloudflare

  1. Create a KV namespace: npx wrangler kv namespace create OAUTH_KV
  2. Follow the prompts to add the KV namespace ID to wrangler.jsonc
  3. Set environment variables:
    • GOOGLE_API_KEY - Your Google API key
    • GOOGLE_SEARCH_ENGINE_ID - Your Google Custom Search Engine ID
  4. Deploy: npm run deploy

Connect to Remote MCP Server

After deployment, you can use MCP Inspector to connect to the remote server:

npx @modelcontextprotocol/inspector@latest

Enter your Workers URL (e.g., your-worker-name.your-account.workers.dev/sse) as the MCP server address and click "Connect".

Connect Claude Desktop to Remote Server

Update the Claude configuration file to point to your Workers URL:

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://your-worker-name.your-account.workers.dev/sse"
      ]
    }
  }
}

Troubleshooting

If you encounter issues:

  1. Restart Claude
  2. Try connecting to the MCP server directly from the command line:
    npx mcp-remote http://localhost:8787/sse
    
  3. Clear the MCP authentication files:
    rm -rf ~/.mcp-auth
    
  4. Check console logs for detailed error information

Developer Notes

  • This project is developed using TypeScript
  • Based on Cloudflare Workers and Durable Objects
  • Integrates OAuth authentication
  • Uses Google Custom Search API for search functionality
  • Includes webpage content extraction and analysis features

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选