url2md is answering right now. Last checked moments ago. 76 installs a week from npm.
PDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309.
Today is the operative word: we check url2md every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add mcp --transport http https://url2md.io/mcp
https://url2md.io/mcp
[mcp_servers.mcp]
url = "https://url2md.io/mcp"
{
"mcpServers": {
"mcp": {
"url": "https://url2md.io/mcp"
}
}
}
{
"servers": {
"mcp": {
"type": "http",
"url": "https://url2md.io/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://url2md.io/mcp | streamable-http | sign-in | 352 ms | 0 min ago |
Web pages to clean Markdown for AI agents, honouring robots.txt and AI opt-outs.
Web pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.
Screenshot web pages, read them as clean Markdown (JS rendered), and render HTML to PDF.
One public web page as clean markdown, with title, language and a SHA-256. Obeys robots.txt.
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.
Answers built from our own checks of this server.