This MCP server enables clean web content extraction from URLs or HTML using Trafilatura, supporting multiple output formats and configurable extraction options.
An MCP server that extracts clean Markdown or HTML content from web pages by stripping away ads, navigation, and clutter. It offers tools to process URLs or raw HTML, returning structured metadata alongside the main article content.
MCP server that retrieves bot-unfriendly page content as Markdown and screenshots as vision-ready image tiles, escalating through increasingly sophisticated extraction tiers (plain HTTP, trafilatura, TLS impersonation, headless Chromium) only as needed.
An MCP server for intelligent web content extraction from JavaScript-heavy sites using single-file and trafilatura. It enables AI agents to fetch, render, and paginate through clean article content and metadata.
Model Context Protocol (MCP) server for web content fetching and extraction. Enables fetching webpages, extracting clean content using Trafilatura, discovering links, and batch fetching up to 10 URLs.