Enables LLMs to retrieve and process web page content, converting HTML into markdown for easier consumption.
Sponsored
This Model Context Protocol (MCP) server empowers Large Language Models (LLMs) to retrieve and process content from web pages. It intelligently fetches web content, converts HTML into easily digestible markdown, and offers advanced options like content truncation, chunked reading via `start_index`, and raw content retrieval. It acts as a bridge, allowing LLMs to seamlessly interact with and understand web-based information.
Características Principales
01Fetches URLs and extracts contents as markdown
02Configurable maximum response length for content truncation
03Supports chunked reading of web pages using a start index
04Option to retrieve raw web content without markdown conversion
05Configurable user-agent, proxy, and robots.txt obedience
060 GitHub stars
Casos de Uso
01Empowering LLMs to access and summarize information from the internet
02Allowing LLMs to read lengthy web pages in segments for detailed analysis
03Integrating web content retrieval into LLM-powered applications and agents
