Crawls websites, saves extracted content as Markdown files and maps site structure and links.
Setup
This project documents no single launch command; follow its repository instructions.
Markdown Web Crawl MCP
jmh108
Related
More- SsearxNcrawlDas Digitale MomentumWeb search through your own SearXNG instance plus crawling of pages and whole sites into deduplicated Markdown, without an API key.Search & Web Data179 Repository stars
- CCrawl4AI MCP ServerBjornMelinA pinned, tested distribution of Crawl4AI with MCP client setup and deployment guidance for web crawling.Search & Web Data30 Repository stars
- CCrawl4AI MCP (TypeScript)omgwtfwowTypeScript MCP server for Crawl4AI with tools for web crawling, content extraction and browser automation.Search & Web Data13 Repository stars
- SScrapeGraph MCP ServerScrapeGraphAIOfficialUses the ScrapeGraphAI API to convert web pages to markdown, extract structured data and run AI web searches.Search & Web DataLocal + remote116 Repository stars
- Ppure.md MCP Serverpure.mdOfficialAccess web content as Markdown and run searches through pure.md, with headless JS rendering and proxy rotation built in.Search & Web Data60 Repository stars
- SSkrape MCPskrape.aiOfficialTurns any URL into clean Markdown for LLMs using skrape.ai, including JavaScript-rendered pages.Search & Web Data12 Repository stars