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.
Fast, token-efficient web content extraction for AI agents - converts websites to clean Markdown while preserving links. Features Mozilla Readability, smart caching, polite crawling with robots.txt support, and concurrent fetching.
Crawl websites into clean Markdown, search pages, and extract structured data with LLMs. Built-in MCP server for web research and RAG pipelines.
Quality signal
53/100 (Fair)
51/100 (Fair)
Install path
npx · high
npx · high
Engagement
1 0 0 157
5 0 1 3
Tools
Content extraction with Mozilla ReadabilityHTML to Markdown conversion with GitHub Flavored Markdown supportSmart caching using SHA-256 hashed URLsPolite crawling with robots.txt support and rate limitingConcurrent fetching with configurable depth and concurrencyStream-first design for low memory usage
Crawls single pages or full websites with URL filteringOutputs clean Markdown files with citations and timestampsGenerates structured JSONL index per pageIncludes local embedding model with zero API key requirementSupports downloading referenced PDFs and DOCX files with filtersImplements HTTP retry with exponential backoff honoring Retry-After headers