CleanText is an MCP server published by net.bigfloppy.cleantext, hosted at cleantext.bigfloppy.net. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 1 tool, including extract.
Extract clean article text or Markdown from any public web page; ads and boilerplate stripped.
26 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Fetch a public web page and return its main article text or Markdown (nav, ads and boilerplate stripped).
| Parameter | Type | Description |
|---|---|---|
| url * | string | Absolute http(s) URL of the page |
| format | string | one of ["text","markdown","json"] |
{
"name": "extract",
"title": "Extract page text",
"description": "Fetch a public web page and return its main article text or Markdown (nav, ads and boilerplate stripped).",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "Absolute http(s) URL of the page"
},
"format": {
"enum": [
"text",
"markdown",
"json"
],
"type": "string",
"default": "markdown"
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.