Site To Markdown

Text REST API MCP

Convert a full web page's HTML into clean Markdown, the way the Site to Markdown page does: navigation, footers, scripts, styles, iframes and SVG are removed, the content root is <main>, <article> or [role="main"] when present, and headings, lists, links, images, code blocks, blockquotes and tables become Markdown. Pass the page HTML (this tool does not fetch) and optionally the page URL so relative links and images resolve to absolute ones. Returns the markdown plus word, line, and character counts.

This page documents the HTTP endpoint POST /api/tools/site-to-markdown/execute. See the MCP reference →

Call it over REST

POST https://api.findutils.com/api/tools/site-to-markdown/execute · no API keys · 60 requests/min per IP

Execute — verified arguments

curl -X POST https://api.findutils.com/api/tools/site-to-markdown/execute \
  -H "Content-Type: application/json" \
  -d '{
    "html": "<main><h1>Title</h1><p>Hello <a href=\"/x\">link</a></p></main>",
    "url": "https://example.com/"
  }'

Parameter schema for this endpoint

curl https://api.findutils.com/api/tools/site-to-markdown

Interactive docs · OpenAPI 3.1 spec · All REST tools

Input schema

Argument Type Required Description
html string yes The page HTML to convert. A full document or a fragment both work.
url string no The page's URL, used only to resolve relative links and image sources. Nothing is fetched.

Example arguments (verified)

{
  "html": "<main><h1>Title</h1><p>Hello <a href=\"/x\">link</a></p></main>",
  "url": "https://example.com/"
}

Also an MCP tool

Claude, Cursor, and any MCP client can call this tool as findutils:site_to_markdown after one connect command.

Connect once

claude mcp add findutils --transport http https://mcp.findutils.com/
Open the MCP reference for Site To Markdown →

More Text tools