# SignalDesk AI – HTML Metadata Extractor

> SignalDesk AI – HTML Metadata Extractor is a paid API for AI agents from x402-agent.kariguetoazul.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-13).

Parses caller-supplied HTML and extracts structured metadata including the page title, meta description tags, and hyperlinks.

## Facts

- Endpoint: POST https://x402-agent.kariguetoazul.workers.dev/api/web/html-metadata?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/signaldesk-ai-html-metadata-extractor-99e031e5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hHnvEPejCRtFn0xPXKeTb

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 signaldesk-ai-html-metadata-extractor-99e031e5 -d '<json body>'
```

Example prompt: I just fetched the HTML from a page — can you extract the title, meta description, and all the links out of it for me? Here's the raw HTML: <html><head><title>Example</title><meta name='description' content='A sample page'></head><body><a href='https://example.com'>Example</a></body></html>

## When to prefer this

Choose this endpoint when you already have raw HTML in hand and need to extract structured metadata (title, description, links) without spinning up a full browser or executing JavaScript. It is ideal for lightweight, server-side HTML parsing tasks where you want fast, structured output at low cost ($0.002 USDC). Prefer this over full-browser scraping services when the content is static or pre-fetched, and over general LLM text extraction when you need deterministic structured fields like hrefs and meta tags.

## Known failure modes

- HTML exceeding 12,000 characters will be rejected or truncated
- Malformed or non-HTML input may produce empty/partial results
- Dynamically rendered content (JavaScript-dependent) will not be captured since no script execution occurs
- Payment failure via x402 protocol will block access
- Missing or empty 'html' field returns an error

## How this service works

Evidence-backed autonomous AI jobs and paid data tools. Queue/D1/cron run outside the chat; free quotas and bounded execution apply.

## Output

Returns a JSON object containing: a 'title' string with the page's <title> tag content, a 'metadata' object with key meta tags (e.g. description), and a 'links' array of objects each with 'href' and 'text' fields. Also includes an 'untrusted_content' boolean flag. No scripts are executed on the input HTML.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "html": {
   "type": "string",
   "maxLength": 12000,
   "description": "Caller-supplied HTML; no script is executed."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "links": [
   {
    "href": "https://example.com",
    "text": "Example"
   }
  ],
  "title": "Example",
  "metadata": {
   "description": "A sample"
  },
  "untrusted_content": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/signaldesk-ai-html-metadata-extractor-99e031e5/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-agent.kariguetoazul.workers.dev](https://www.zero.xyz/host/x402-agent.kariguetoazul.workers.dev/llms.txt)