# AgentShelf CSS Cite Extractor

> AgentShelf CSS Cite Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-02).

Extracts text content from all <cite> elements on a given public webpage or raw HTML string

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/css-cite?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-css-cite-extractor-136f8f91
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_CoMfWR2GkD6fNOZaCt1lx

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-css-cite-extractor-136f8f91 -d '<json body>'
```

Example prompt: Can you pull out all the <cite> element text from https://en.wikipedia.org/wiki/Machine_learning for me?

## When to prefer this

Use this endpoint when you specifically need to extract <cite> element text from a public webpage or HTML blob in an SSRF-safe way. Prefer the free sandbox variant (POST /v1/sandbox/css-cite) for testing before incurring the $0.001 USDC cost. Choose this over generic HTML scrapers when you need just citation elements without full-page content, and when SSRF safety is a requirement.

## Known failure modes

- URL is not publicly accessible or returns a non-200 status — extraction fails
- SSRF protection blocks private/internal IP ranges — request rejected
- HTML contains no <cite> elements — returns empty list
- HTML exceeds 200,000 character limit — request rejected
- URL string is malformed or under 8 characters — validation error
- Network timeout fetching the target URL — request fails

## How this service works

Call when an agent needs cite text via cite from a public page or HTML (SSRF-safe). Exact $0.001 USDC. Prefer unpaid POST /v1/sandbox/css-cite first.

## Output

A list of text strings extracted from all <cite> elements found in the provided URL's HTML or the supplied raw HTML. Returns citation text content suitable for downstream citation analysis, reference listing, or content auditing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 8,
   "description": "Public page to fetch. The selector or profile is fixed by the SKU. Provide url or html."
  },
  "html": {
   "type": "string",
   "examples": [
    "<!doctype html><html lang=\"en\"><head><title>Hello</title>\n<meta charset=\"utf-8\"><meta name=\"description\" content=\"Desc\">\n<link rel=\"canonical\" href=\"https://example.com/\"><link rel=\"icon\" href=\"/favicon.ico\">\n</head><body><h1>Hello</h1><a href=\"https://example.com/a\">A</a></body></html>"
   ],
   "maxLength": 200000,
   "minLength": 1,
   "description": "HTML to extract from locally. Provide html or url. When both are set, html is used."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-css-cite-extractor-136f8f91/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)