# AgentRead by Rowan Vale

> AgentRead by Rowan Vale is a paid API for AI agents from agent-read.toolschemaforge.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-31).

Fetches a public URL, converts its content to clean LLM-ready markdown, and optionally scans it for prompt-injection risks

## Facts

- Endpoint: GET https://agent-read.toolschemaforge.workers.dev/v1/read?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentread-by-rowan-vale-126d3d34
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_sFlOR1j5kt3HhFivopoaU

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentread-by-rowan-vale-126d3d34
```

Example prompt: Fetch https://en.wikipedia.org/wiki/Markdown, convert it to clean markdown, and scan it for prompt-injection risks so I can safely pass it to my LLM pipeline.

## When to prefer this

Choose this endpoint when your agent needs to safely ingest arbitrary public web pages into an LLM context — especially when you want both clean markdown output AND a built-in prompt-injection safety check in a single call. It is ideal for agentic pipelines that browse the open web and need to guard against malicious content embedded in external pages. Prefer it over generic HTTP fetch utilities when LLM-readiness and security scanning matter; prefer it over raw HTML scrapers when you need token-efficient, structured text output without writing your own HTML-to-markdown parser.

## Known failure modes

- URL is not publicly accessible or returns a non-200 HTTP status — endpoint will likely return an error or empty markdown
- Content-type is not parseable as text/HTML (e.g. binary files, PDFs) — markdown conversion may fail or return garbage
- max_tokens budget too small for the document — response will be truncated with truncated:true
- Prompt-injection scan may produce false positives on legitimate technical content containing instruction-like language
- Rate limiting or upstream timeout if the target URL is slow to respond

## How this service works

Clean, LLM-ready markdown and prompt-injection scanning for agents.

## Output

A JSON object containing: the cleaned markdown text of the fetched page, its title, the source URL, an estimated token count, a truncation flag, and (if scan=true) a prompt-injection risk assessment with a risk level (low/medium/high), a numeric score, and an array of detected injection signals.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "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."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "scan": {
   "risk": "low",
   "score": 0,
   "signals": []
  },
  "title": "Example",
  "markdown": "# Example\n\nCleaned article text.",
  "truncated": false,
  "source_url": "https://example.com/article",
  "tokens_est": 8
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentread-by-rowan-vale-126d3d34/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-read.toolschemaforge.workers.dev](https://www.zero.xyz/host/agent-read.toolschemaforge.workers.dev/llms.txt)