Web Scraper

Part of the Sovereign MCP Servers collection, this gives Claude four web scraping operations: fetch URLs, extract text and links, pull metadata, and run CSS selectors against pages. It's the kind of tool you'd wire up when you need to programmatically pull content from documentation sites, analyze competitor pages, or extract structured data from HTML without writing your own scraper. Ships as a single npx command and runs over stdio. The parent repository includes 33 other utility servers ranging from JSON processing to Git helpers, all following the same one-command deployment pattern. Useful for quick web data extraction tasks where you want LLM-assisted scraping without managing headless browsers or parsing libraries yourself.