Webcrawl

Webcrawl (mcp-server-webcrawl) is an open-source MCP (Model Context Protocol) server that enables Claude Desktop and compatible agents to access and query archived or crawled website data from multiple formats and crawling tools, such as ArchiveBox, HTTrack, InterroBot, Katana, SiteOne, WARC, and wget. It is designed for developers or technically proficient users who wish to make web-scraped or historically archived content available to AI agents for advanced search, data extraction, or analysis use cases.