Read any URL as markdown (readm3.com)
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 document by URL and return its text: PDFs (arXiv papers, reports), web pages, Word, Excel, PowerPoint, OpenDocument, EPUB, Markdown and other text. Use it to summarize, quote or answer questions about a link. Returns title, kind, page count, character count, whether the text was truncated, and the text. maxChars caps the text (default 100,000, up to 400,000). No account needed; a free hourly allowance, then an x402 reader pass.
An http(s) URL on the public internet.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http readm3 https://readm3.com/mcp
Fetch a document by URL and return its text: PDFs (arXiv papers, reports), web pages, Word, Excel, PowerPoint, OpenDocument, EPUB, Markdown and other text. Use it to summarize, quote or answer questions about a link. Returns title, kind, page count, character count, whether the text was truncated, and the text. maxChars caps the text (default 100,000, up to 400,000). No account needed; a free hourly allowance, then an x402 reader pass.
| Argument | Type | Description |
|---|
| url* | string | An http(s) URL on the public internet. |
| maxChars | integer |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "An http(s) URL on the public internet."
},
"maxChars": {
"type": "integer",
"maximum": 400000,
"minimum": 1000
}
},
"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 11, 2026.