Open-source web scraper and extraction MCP server with JavaScript rendering, markdown output, PDF/DOCX parsing, structured errors, and validated extraction contract diagnostics for agents.
A Model Context Protocol server that lets Claude query arbitrary webpages with token-efficient, structure-aware retrieval, reducing token costs by fetching only relevant sections.
A lightweight web scraping server that allows Claude Desktop users to extract various types of data from websites, including text, links, images, tables, headlines, and metadata using CSS selectors.