Read web pages and PDFs as clean Markdown for AI agents. Pay per call in USDC via x402, no API key.
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 and return its readable content as JSON: plain text or Markdown (headings, lists, links kept), plus title, description, author, publish date, site name, language and preview image. Ads, menus and scripts are stripped. Also reads PDF, Word, Excel and CSV links. Failed fetches are not charged. Price: $0.002 USDC (x402).
Public http(s) page or document to read
markdown (default here: keeps headings, lists and links) or text
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.
claude mcp add --transport http agent-read-proxy https://agent-read-proxy.agent-read-proxy.workers.dev/mcp
Fetch a public web page and return its readable content as JSON: plain text or Markdown (headings, lists, links kept), plus title, description, author, publish date, site name, language and preview image. Ads, menus and scripts are stripped. Also reads PDF, Word, Excel and CSV links. Failed fetches are not charged. Price: $0.002 USDC (x402).
| Argument | Type | Description |
|---|---|---|
| url* | string | Public http(s) page or document to read |
| format | string | markdown (default here: keeps headings, lists and links) or text |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) page or document to read"
},
"format": {
"enum": [
"text",
"markdown"
],
"type": "string",
"default": "markdown",
"description": "markdown (default here: keeps headings, lists and links) or text"
}
},
"additionalProperties": false
}Read up to 5 public web pages or documents (PDF, Word, Excel, CSV) in one call, in parallel. Returns each one's readable text or Markdown plus metadata, and lists any that failed. Charged only if at least one URL was read. Price: $0.006 USDC (x402).
| Argument | Type | Description |
|---|---|---|
| urls* | array | 1 to 5 public http(s) URLs |
| format | string | markdown (default here: keeps headings, lists and links) or text |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"maxItems": 5,
"minItems": 1,
"description": "1 to 5 public http(s) URLs"
},
"format": {
"enum": [
"text",
"markdown"
],
"type": "string",
"default": "markdown",
"description": "markdown (default here: keeps headings, lists and links) or text"
}
},
"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 Oct 31, 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.