# AgentShelf JSON-LD Extractor

> AgentShelf JSON-LD Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-02).

Extracts JSON-LD structured data blocks from a public web page URL or raw HTML content, safely guarded against SSRF.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/extract-jsonld?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-json-ld-extractor-64561a49
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Q4J4Pi-XZMQ60FyV3OaB-

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 agentshelf-json-ld-extractor-64561a49 -d '<json body>'
```

Example prompt: Can you extract all the JSON-LD structured data blocks from https://example.com/product/widget-pro and show me what schema types are present?

## When to prefer this

Use this endpoint when you need to reliably extract JSON-LD structured data from a public URL or raw HTML without setting up your own scraping infrastructure. It is SSRF-safe making it suitable for agent pipelines that accept user-supplied URLs. Prefer the unpaid sandbox POST /v1/sandbox/extract-jsonld first for testing; use this paid endpoint for production or high-volume extraction where the $0.004 USDC per-call cost is acceptable.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails with an error
- No JSON-LD blocks present on the page — returns empty array
- URL targets a private or internal IP range — blocked by SSRF protection
- HTML input exceeds 200,000 character limit — request rejected
- Malformed HTML prevents parsing — partial or empty results returned

## How this service works

Call when an agent needs JSON-LD blocks extracted from a public page or HTML (SSRF-safe). Exact $0.004 USDC. Prefer unpaid POST /v1/sandbox/extract-jsonld first.

## Output

Returns an array of JSON-LD objects parsed from the page's <script type='application/ld+json'> blocks, preserving their full structure including @context, @type, and all nested properties.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 8,
   "description": "Public http(s) URL to fetch. When html is also sent, this is only the base for relative links. Provide url or html."
  },
  "html": {
   "type": "string",
   "examples": [
    "<script type=\"application/ld+json\">{\"@type\":\"Article\"}</script>"
   ],
   "maxLength": 200000,
   "minLength": 1,
   "description": "HTML to parse locally instead of fetching. When both html and url are set, html is used. Provide html or url."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-json-ld-extractor-64561a49/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)