# Syntexa AgentShelf Readability Extractor

> Syntexa AgentShelf Readability Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-02).

Fetches a public URL and returns Mozilla Readability-parsed article content as Markdown, plus title, byline, excerpt, and final URL — SSRF-safe, paid via x402.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/readability?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/syntexa-agentshelf-readability-extractor-5dd79502
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_g5mR1qC9IPfUXOgVtlMLV

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 syntexa-agentshelf-readability-extractor-5dd79502 -d '<json body>'
```

Example prompt: Can you fetch the article at https://example.com/news/some-article and give me the clean readable text as markdown, along with the title and author?

## When to prefer this

Choose this endpoint when you need clean, reader-mode article text from a public URL in Markdown format, especially when you also need structured metadata like title, byline, and excerpt. It is SSRF-safe making it suitable for untrusted user-supplied URLs. Prefer the free sandbox endpoint (/v1/sandbox/readability) for testing before paying. Prefer this over generic scraping tools when the goal is article content rather than raw HTML or structured data extraction.

## Known failure modes

- URL is behind a paywall or login wall — returns empty or minimal content
- URL resolves to a non-article page (homepage, search results) — Readability may return little or no content
- SSRF-protected: private/internal IP ranges and localhost URLs are rejected
- URL is malformed or unreachable — returns an error
- Dynamic JavaScript-rendered content may not be fully captured
- URL exceeds 2048 character limit — rejected by schema validation

## How this service works

Call when an agent needs Mozilla Readability article markdown from a public URL, plus title, byline, excerpt, and final_url. SSRF-safe. Exact $0.005 USDC. Prefer unpaid POST /v1/sandbox/readability first.

## Output

Returns structured JSON containing the article body as Markdown text, the article title, byline (author), a short excerpt, and the final resolved URL after any redirects — all extracted using Mozilla Readability.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "examples": [
    "https://example.com/article"
   ],
   "maxLength": 2048,
   "minLength": 8,
   "description": "Public http(s) URL to fetch. Private, localhost, link-local, and metadata hosts are rejected."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/syntexa-agentshelf-readability-extractor-5dd79502/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)