# AgentShelf Profile Cite – Web Page Citation Extractor

> AgentShelf Profile Cite – Web Page Citation Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.007/call, status unknown (last checked 2026-10-02).

Extracts citable text from a public web page URL or raw HTML, with SSRF protection, for use in agent-generated citations.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/profile-cite?utm_source=zero.xyz
- Price: $0.007/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-profile-cite-web-page-citation-extractor-ad603fb6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qhC9KUIwl5S0PJNhi2YNw

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-profile-cite-web-page-citation-extractor-ad603fb6 -d '<json body>'
```

Example prompt: Can you extract the citable text from this article so I can reference it in my report? Here's the URL: https://example.com/some-public-article

## When to prefer this

Use this endpoint when an agent needs to extract clean, citable text from a publicly accessible URL or raw HTML content, particularly when SSRF safety is required. Prefer the free sandbox endpoint (/v1/sandbox/profile-cite) for testing. Choose this paid endpoint ($0.007 USDC) for production workloads where reliability and SSRF-safe fetching of public pages is needed for citation generation.

## Known failure modes

- URL is not publicly accessible or requires authentication — returns an error
- URL triggers SSRF detection (private/internal IP range) — blocked for security
- HTML input exceeds 200,000 character limit — returns validation error
- Malformed or empty URL/HTML input — returns input validation error
- Target page returns non-200 status — may return partial content or error
- Page content is primarily non-text (e.g. images, PDFs) — extracted text may be empty or minimal

## How this service works

Call when an agent needs cite text extracted from a public page or HTML (SSRF-safe). Exact $0.007 USDC. Prefer unpaid POST /v1/sandbox/profile-cite first.

## Output

Returns the extracted citable text content from the provided URL or HTML input, stripped of markup and irrelevant boilerplate, ready for use as a citation or reference passage in agent-generated documents.

## 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 name=\"description\" content=\"Desc\"><meta property=\"og:title\" content=\"OG\">\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-profile-cite-web-page-citation-extractor-ad603fb6/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)