Paid read_page tool: a public web page as clean markdown, $0.002 per delivered page over x402.
Maintained by@domondi1(verified)Also a maintainer?
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.
Read one public web page as clean, LLM-ready markdown (title, main text, headings, lists, links, tables) with word count and a content hash. Paid per delivered page over x402; a blocked, missing, failing or refused page costs nothing.
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 inferrail-web-read https://inferrail-cost-gateway.onrender.com/read/mcp/
Read one public web page as clean, LLM-ready markdown (title, main text, headings, lists, links, tables) with word count and a content hash. Paid per delivered page over x402; a blocked, missing, failing or refused page costs nothing.
| Argument | Type | Description |
|---|---|---|
| url* | string | |
| request_id | any |
{
"type": "object",
"title": "read_pageArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Request Id",
"default": null
}
}
}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 20, 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.