Convert a web page or HTML into clean readable Markdown for LLM context. $0.005 USDC via x402.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Fetch a public web page by URL and extract clean, readable Markdown for LLM context. Strips scripts, navigation, footers, and chrome. Does not run JavaScript or load a browser. Costs $0.005 USDC on Base, paid with x402.
http(s) URL of a public HTML page to scrape and extract as Markdown
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http pagetext https://pagetext.apexlabs-cloudflare.workers.dev/mcp
Fetch a public web page by URL and extract clean, readable Markdown for LLM context. Strips scripts, navigation, footers, and chrome. Does not run JavaScript or load a browser. Costs $0.005 USDC on Base, paid with x402.
| Argument | Type |
|---|
| Description |
|---|
| url* | string | http(s) URL of a public HTML page to scrape and extract as Markdown |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "http(s) URL of a public HTML page to scrape and extract as Markdown"
}
},
"additionalProperties": false
}Convert raw HTML into clean, readable Markdown for LLM context. Strips scripts, navigation, footers, and chrome. Costs $0.005 USDC on Base, paid with x402.
| Argument | Type | Description |
|---|---|---|
| html* | string | Raw HTML to convert into clean readable Markdown |
{
"type": "object",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"description": "Raw HTML to convert into clean readable Markdown"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 16, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.