Complete AI Training

MCP server · Research

MarkCrawl MCP server

by AIMLPM

Turn websites into clean Markdown your AI can read, search and quote.

Flow diagram: you ask your AI “Crawl the docs at docs.example.com into my output folder”, on your own computer the MarkCrawl MCP server works with websites, and you get back clean Markdown files.

MarkCrawl is a tool that copies a web page or a whole website and turns it into tidy Markdown text, the kind of plain text your AI reads best. This MCP server is the part that lets your AI use MarkCrawl for you. It is handy if you do research, gather documentation, or feed a chatbot with your own pages.

What is an MCP server? The 30-second version

On its own, your AI can only chat with what it already knows. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one connects your AI to MarkCrawl, a website-to-Markdown crawler. So when you ask your AI to read or gather pages from a site, it can actually go and do that instead of guessing.

What this MCP server does

You ask your AI to grab a page or crawl a site. Your AI passes that request to this helper. The helper runs MarkCrawl, which fetches the pages, strips out menus, ads and scripts, and saves clean Markdown files plus a small index. Your AI then reads that clean text and answers you, or keeps it for later use in a chatbot or search setup.

Flow diagram: you ask your AI “Crawl the docs at docs.example.com into my output folder”, on your own computer the MarkCrawl MCP server works with websites, and you get back clean Markdown files. Click to zoom

What you can do with it

  • Turn a single web page into clean Markdown text
  • Crawl a whole site or just a section of it
  • Save each page as a file with a ready-made citation and date
  • Skip pages you do not want using include and exclude rules
  • Download linked PDFs, Word files or images along the way
  • Take a screenshot of a page when you need to see it
  • Resume a crawl that stopped partway through

Try asking your AI

  • “Crawl the docs at docs.example.com and save the Markdown to my output folder”
  • “Grab just this one page and give me the clean text”
  • “Crawl this blog but skip anything under /news”
  • “Pull the first 50 pages of this site and list what you found”

What it gives back to you

You get clean Markdown files, one per page, each with a citation and the date it was fetched. You also get a small index file that lists every page with its URL, title and text. In the chat, your AI can show you a summary, a list of pages, or quote the parts you asked about.

Before you start

What you need

  • Python installed on your computer
  • MarkCrawl installed with the MCP add-on (pip install markcrawl[mcp])
  • An AI app that can connect to MCP servers, like Claude Desktop

Good to know

Crawling a site can take a while and uses your internet connection, so be respectful of sites you do not own and check their rules first.

Install it with your AI

Add MarkCrawl MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check MarkCrawl MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

People who do web research, gather documentation, or build small chatbots from their own pages, without wanting to write code.