A Node.js tool based on Playwright that can bypass search engine anti - scraping mechanisms to perform Google searches and extract results. It can be used as a command - line tool or an MCP server to provide real - time search capabilities for AI assistants.

This project is an MCP server designed for the Google Programmable Search Engine (PSE) API, providing a web search tool to compatible clients (such as VSCode, Copilot, etc.) through the MCP protocol.

Google Custom Search Engine MCP Server provides search capabilities for LLMs

MCP-GetWeb is a protocol server that provides web search and content extraction functions, supporting multiple search engines such as DuckDuckGo, Google, and Felo AI, and can crawl URL content, extract metadata, and convert it into Markdown format.

This is an implementation of the scientific search MCP protocol designed for the Cursor editor, integrating multiple academic search engines (such as Google Scholar, PubMed, arXiv, etc.), supporting Semantic Scholar search through Tor, and providing functions such as PDF processing.

The Search Fusion MCP Server is a highly available multi-engine search aggregation service that provides intelligent failover, a unified API, and LLM-optimized content processing. It supports 7 search engines such as Google, Serper, and Jina AI, and has advanced functions such as concurrency control, connection pool management, and automatic proxy detection.