Wet

Wet (Web Extended Toolkit MCP Server) is an open-source MCP server designed for AI agents to provide advanced web search, multi-strategy content extraction, and automatic library documentation indexing. It operates without API keys using built-in local models but can be connected to cloud providers for more advanced features. Its capabilities include stealth web scraping, local file conversion to markdown, batch processing, citation generation, and support for research sources like Google Scholar and arXiv. Wet is aimed at developers, data researchers, and AI engineers wanting reliable, privacy-first data access and extraction pipelines for autonomous or agentic AI applications.