google-search MCP Server

Use This MCP server To

Look up current information without paying for a search service Ask my assistant to check today's news on a topic Research a question and get real links I can follow Compare what several sites say about the same product Find recent pages the model would not otherwise know about

README

Google Search Tool

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.

中文文档

Key Features

Local SERP API Alternative: No need to rely on paid search engine results API services, all searches are executed locally
Advanced Anti-Bot Detection Bypass Techniques:
- Intelligent browser fingerprint management that simulates real user behavior
- Automatic saving and restoration of browser state to reduce verification frequency
- Smart headless/headed mode switching, automatically switching to headed mode when verification is needed
- Randomization of device and locale settings to reduce detection risk
Raw HTML Retrieval: Ability to fetch the raw HTML of search result pages (with CSS and JavaScript removed) for analysis and debugging when Google's page structure changes
Page Screenshot: Automatically captures and saves a full-page screenshot when saving HTML content
MCP Server Integration: Provides real-time search capabilities to AI assistants like Claude without requiring additional API keys
Completely Open Source and Free: All code is open source with no usage restrictions, freely customizable and extensible

Technical Features

Developed with TypeScript, providing type safety and better development experience
Browser automation based on Playwright, supporting multiple browser engines
Command-line parameter support for search keywords
MCP server support for AI assistant integration
Returns search results with title, link, and snippet
Option to retrieve raw HTML of search result pages for analysis
JSON format output
Support for both headless and headed modes (for debugging)
Detailed logging output
Robust error handling
Browser state saving and restoration to effectively avoid anti-bot detection

Installation

# Install from source
git clone https://github.com/web-agent-master/google-search.git
cd google-search
# Install dependencies
npm install
# Or using yarn
yarn
# Or using pnpm
pnpm install

# Compile TypeScript code
npm run build
# Or using yarn
yarn build
# Or using pnpm
pnpm build

# Link package globally (required for MCP functionality)
npm link
# Or using yarn
yarn link
# Or using pnpm
pnpm link

google-search FAQ

Do I need a paid key?

No, and that is the main appeal. Searches run through a browser on your own computer rather than a paid search provider.

How hard is setup?

Fairly hard. You download the code, build it, link it on your system, then paste a block into Claude Desktop's config file.

Which apps does it work with?

Claude Desktop is the documented one. Other apps that run MCP servers should work with the same command.

Can I use this to research a topic and get sources?

Yes. It returns the title, link and summary line for each result, so you can open the sources yourself.

Will Google block it?

Sometimes. It tries to behave like a normal person browsing and opens a visible window when Google asks for a human check.

Is it still maintained?

The code has not been updated since April 2025. Google reshuffles its results pages often, so it may need fixes to keep working.

Does it use my own Google account?

No. It runs a separate browser session and saves that session so it gets asked to verify less often.