AgentRead is an MCP server published by dev.workers.toolschemaforge.agent-read, hosted at agent-read.toolschemaforge.workers.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 2 tools, including read_url, scan_text.
Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
1 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Read a public web page or document and return clean, LLM-ready markdown. Pricing: $0.001 (1 sat) per read, or $0.003 (3 sats) when scan is true. The free tier applies first, shared with the HTTP API and all MCP tools.
| Parameter | Type | Description |
|---|---|---|
| url * | string | Public http(s) URL of the document to read. |
| scan | boolean | Also scan the converted document for prompt-injection risk. |
| max_tokens | integer | Optional output token budget. |
{
"name": "read_url",
"title": "Read URL",
"description": "Read a public web page or document and return clean, LLM-ready markdown. Pricing: $0.001 (1 sat) per read, or $0.003 (3 sats) when scan is true. The free tier applies first, shared with the HTTP API and all MCP tools.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public http(s) URL of the document to read."
},
"scan": {
"type": "boolean",
"description": "Also scan the converted document for prompt-injection risk."
},
"max_tokens": {
"type": "integer",
"maximum": 1000000,
"minimum": 1,
"description": "Optional output token budget."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"markdown",
"title",
"source_url",
"tokens_est",
"truncated"
],
"properties": {
"scan": {
"type": "object",
"required": [
"risk",
"score",
"signals"
],
"properties": {
"risk": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
},
"score": {
"type": "number"
},
"signals": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"title": {
"type": [
"string",
"null"
]
},
"markdown": {
"type": "string"
},
"truncated": {
"type": "boolean"
},
"source_url": {
"type": [
"string",
"null"
]
},
"tokens_est": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
}
}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.
Scan text for prompt-injection risk and return a risk level, score, and signals. Pricing: $0.002 (2 sats) per scan. The free tier applies first, shared with the HTTP API and all MCP tools.
| Parameter | Type | Description |
|---|---|---|
| text * | string | Text to scan for prompt-injection risk. |
{
"name": "scan_text",
"title": "Scan text",
"description": "Scan text for prompt-injection risk and return a risk level, score, and signals. Pricing: $0.002 (2 sats) per scan. The free tier applies first, shared with the HTTP API and all MCP tools.",
"inputSchema": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 200000,
"minLength": 1,
"description": "Text to scan for prompt-injection risk."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"risk",
"score",
"signals"
],
"properties": {
"risk": {
"enum": [
"low",
"medium",
"high"
],
"type": "string"
},
"score": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"signals": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}
}AgentRead by Rowan Vale converts public web pages and documents into clean markdown and scans text for prompt-injection risk. Each IP gets a free daily quota shared with the HTTP API. After the free tier, reads cost $0.001 (1 sat) and scans cost $0.002 (2 sats). Pay with x402 exact USDC on Base through PayAI, or create a Lightning invoice at POST /v1/invoice and retry with the X-Lightning-Invoice header.
Names, descriptions and schemas were written by the server and are shown as data.