AI / MLTypeScript

google-search

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches.

Free
N/A rating (0 reviews)0 installs575 GitHub stars
Google SearchWeb ScrapingPlaywright

This tool serves as a local alternative to paid search engine results APIs, allowing users to perform Google searches without relying on external services. It employs advanced techniques to bypass anti-bot detection, ensuring that searches are executed seamlessly and efficiently. The tool also integrates as a Model Context Protocol (MCP) server, providing real-time search capabilities for AI assistants like Claude, making it a versatile solution for developers and users alike. In addition to executing searches, the tool offers features such as raw HTML retrieval for debugging, automatic screenshot capturing of search result pages, and intelligent browser fingerprint management. With its open-source nature, users can customize and extend the tool to meet their specific needs, all while enjoying a completely free solution.

Compatible with

Claude DesktopCursor

Install

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-google-search"
      ]
    }
  }
}

Config File Location

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

Windows: %APPDATA%\Claude\claude_desktop_config.json

Linux: ~/.config/claude/claude_desktop_config.json

Some servers require additional setup - check the GitHub README for specific instructions.

Permissions

ok0
ok1
google-search MCP Server — MCPNest — MCPNest