A Model Context Protocol (MCP) server that provides web content fetching using the Defuddle library. It removes webpage clutter, extracts the main content, and preserves the page title and key metadata. It can output either clean Markdown or raw HTML, depending on the request, offering flexible output options. The server supports chunked reading and pagination via start_index and max_length, enabling partial content retrieval. In addition to content, it provides rich metadata such as title, author, publication date, word count, domain, and processing time. It is a drop-in replacement for the default fetch MCP server (which uses Readability.js) and generally yields better results for modern web pages. It includes a defined fetch tool that fetches a URL and returns the processed content along with metadata. It is configurable for integration with Claude Desktop and other MCP-enabled clients.