# agent-reader Web Content Extractor

> agent-reader Web Content Extractor is a paid API for AI agents from x402.fenixfoundry.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Fetches any public web page and returns clean, LLM-ready Markdown with metadata (title, author, date, excerpt, links, word count) stripped of boilerplate.

## Facts

- Endpoint: POST https://x402.fenixfoundry.com/extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-reader-web-content-extractor-ed75d5b4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ir3Bjh7828SZ_Dk5eiKdF

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 agent-reader-web-content-extractor-ed75d5b4 -d '<json body>'
```

Example prompt: Can you fetch the article at https://www.nytimes.com/2024/05/01/technology/ai-agents.html and return it as clean markdown so I can summarize it?

## When to prefer this

Choose this endpoint when you need to retrieve and clean the readable content of a specific public web URL for LLM consumption, especially when you want structured metadata (author, date, links) alongside the article body. Prefer it over raw HTTP fetches when boilerplate removal and markdown conversion are needed. Not suitable for crawling entire sites or authenticated/paywalled content.

## Known failure modes

- Page is behind a login or paywall — returns empty or partial content
- URL is invalid or unreachable — HTTP error or timeout
- Page is JavaScript-heavy SPA — may return incomplete content if JS rendering is not supported
- Rate limiting or bot-detection on target site — fetch may fail or return CAPTCHA page
- Non-article pages (homepages, dashboards) — metadata fields may be empty or inaccurate

## How this service works

Scrape and fetch any public web page and return clean, LLM-ready Markdown plus metadata (title, author, published date, excerpt, outbound links, word count). A web reader and content extractor with boilerplate, nav and ads removed.

## Output

Returns either a Markdown-formatted article body with cleaned prose (boilerplate, navigation, and ads removed) plus metadata fields (title, author, published date, excerpt, outbound links, word count), or a JSON object with only the metadata fields if format=json is specified.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Absolute http(s) URL of the page to fetch and extract."
  },
  "format": {
   "enum": [
    "markdown",
    "json"
   ],
   "type": "string",
   "default": "markdown",
   "description": "`markdown` returns the article body as Markdown; `json` returns metadata only with the markdown omitted."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-reader-web-content-extractor-ed75d5b4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.fenixfoundry.com](https://www.zero.xyz/host/x402.fenixfoundry.com/llms.txt)