Google Search Tool
@web-agent-master
About Google Search Tool
A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"google-search": {
"command": "npx",
"args": [
"google-search-cli",
"search keywords"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Google Search Tool?
Google Search Tool is a Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches and extract results. It can be used directly as a command-line tool or as a Model Context Protocol (MCP) server to provide real-time search capabilities to AI assistants like Claude.
How to use Google Search Tool?
Install from source, build with pnpm build, then run google-search "search keywords" with optional flags (e.g., --limit, --timeout, --get-html). For MCP integration, configure your Claude Desktop’s claude_desktop_config.json with the command npx google-search-mcp (or alternative Windows configurations).
Key features of Google Search Tool
- Local SERP API alternative, no paid API needed
- Advanced anti-bot detection bypass techniques
- Raw HTML retrieval for search result page analysis
- Page screenshot capture when saving HTML content
- MCP server integration for AI assistants like Claude
- Completely open source and free
Use cases of Google Search Tool
- Provide real-time Google search to Claude without additional API keys
- Replace paid SERP APIs with a local, self-hosted solution
- Debug and analyze Google’s page structure when changes occur
- Automate search result extraction while avoiding anti-scraping blocks
- Enable AI assistants to perform web searches directly
FAQ from Google Search Tool
How is this different from commercial SERP APIs like SerpAPI?
It is completely free and open source, runs locally, and does not require any API keys or per-request payments.
What are the runtime requirements?
Node.js v16 or higher, and Playwright browsers (installed automatically on first use). The tool also needs an internet connection to reach Google.
Does it comply with Google’s terms of service?
The tool is provided for learning and research purposes. Users are expected to comply with Google’s terms, avoid sending requests too frequently, and respect rate limits.
How does it handle Google’s anti-bot detection?
It uses intelligent browser fingerprint management, state saving/restoration
Frequently asked questions
How is this different from commercial SERP APIs like SerpAPI?
It is completely free and open source, runs locally, and does not require any API keys or per-request payments.
What are the runtime requirements?
Node.js v16 or higher, and Playwright browsers (installed automatically on first use). The tool also needs an internet connection to reach Google.
Does it comply with Google’s terms of service?
The tool is provided for learning and research purposes. Users are expected to comply with Google’s terms, avoid sending requests too frequently, and respect rate limits.
How does it handle Google’s anti-bot detection?
It uses intelligent browser fingerprint management, state saving/restoration
Basic information
More Search MCP servers
Exa MCP Server 🔍
exa-labsExa MCP for web search and web crawling!
G-Search MCP
jae-jaeA powerful MCP server for Google search that enables parallel searching with multiple keywords simultaneously.
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.
patent-literature-search-mcp
patsnapA professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.
Version 2.0 is here!!
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
Comments