Google Search MCP
by modelcontextprotocol-servers
A Playwright-based Model Context Protocol (MCP) tool that bypasses search engine anti-bot mechanisms and performs Google searches. It extracts results, providing real-time search capabilities for AI assistants.
Last updated: N/A
What is Google Search MCP?
The Google Search MCP server is a tool that allows AI assistants to perform Google searches and extract results in real-time. It uses Playwright to control a Chromium browser, bypasses anti-bot mechanisms, and implements the Model Context Protocol for easy integration.
How to use Google Search MCP?
To use the server, you can install it globally or project-specifically using npx. For global installation, run npx -y @mcp-server/google-search-mcp@latest. For project-specific installation, add an .cursor/mcp.json file with the necessary configuration. You can then configure your Cursor IDE to use the server.
Key features of Google Search MCP
Anti-Bot Bypass
Automatic CAPTCHA Handling
State Persistence
Adaptability
MCP Integration
Multi-language Support
Use cases of Google Search MCP
Providing real-time search results to AI assistants
Enabling AI assistants to answer questions based on current information
Automating research tasks
Integrating search functionality into AI-powered applications
FAQ from Google Search MCP
What parameters does the search tool accept?
What parameters does the search tool accept?
The tool accepts query (required), limit (optional), timeout (optional), language (optional), and region (optional) parameters.
How does the tool bypass anti-bot detection?
How does the tool bypass anti-bot detection?
It uses browser fingerprint spoofing and real user behavior simulation to avoid detection.
What happens when a CAPTCHA is encountered?
What happens when a CAPTCHA is encountered?
The tool automatically switches to headed mode, allowing users to complete the verification.
Where is the browser state saved?
Where is the browser state saved?
By default, the browser state is saved in the .google-search-browser-state.json file in the user's home directory.
What should I do if I encounter rate limiting?
What should I do if I encounter rate limiting?
Avoid making overly frequent search requests, as this may trigger Google's rate limiting mechanisms.