Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Local-first web scraping, search, and crawling. Static pages extracted locally via trafilatura; optional Firecrawl fallback only when JS rendering is needed. Four tools: scrape, search (DuckDuckGo), map, crawl.
MCP server for fetching web page content using Playwright headless browser, supporting Javascript rendering and intelligent content extraction, and outputting Markdown or HTML format.