# AgentProof Extract Page Facts

> AgentProof Extract Page Facts is a paid API for AI agents from agentproof.hatchable.site, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-11).

Extracts structured facts from a web page with a cryptographic provenance receipt and integrity hash for autonomous transaction trust.

## Facts

- Endpoint: POST https://agentproof.hatchable.site/api/paid/extract_page_facts?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentproof-extract-page-facts-9fa007a6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AGSEAms_fh4-TSRaI-1eZ

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 agentproof-extract-page-facts-9fa007a6 -d '<json body>'
```

Example prompt: Pull the key facts from https://example.com/product-page and give me a provenance receipt with a SHA-256 integrity hash so I can prove what the page said right now.

## When to prefer this

Choose this endpoint when an autonomous agent needs not just extracted facts but a cryptographically verifiable provenance record proving what a web page said at a specific moment — especially for AI-to-AI transactions, compliance audits, purchase decisions, or any scenario where disputed page content could arise. Prefer it over plain scrapers when the integrity and auditability of the source data matters as much as the data itself.

## Known failure modes

- URL is unreachable or returns non-200 status — extraction fails with error
- Page content is dynamic/JS-rendered and cannot be captured server-side
- Payment of $0.05 USDC not confirmed via x402 — request rejected
- Rate limiting or quota exceeded — returns error response
- SHA-256 hash cannot be computed if page returns binary/non-text content
- Receipt UUID collision or storage failure — rare but possible

## How this service works

AgentProof publishes Agent Transaction Passport™ and provides machine-paid evidence, provenance receipts, source comparison and change monitoring for autonomous transactions.

## Output

A JSON object containing 'ok' (boolean success), 'tool' name ('extract_page_facts'), a 'receipt' object with a unique UUID and a SHA-256 integrity hash of the extracted content, and a 'service' label ('AgentProof'). The receipt serves as a cryptographic provenance artifact proving what the page contained at extraction time.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "format": "uri"
  },
  "claim": {
   "type": "string"
  },
  "email": {
   "type": "string"
  },
  "phone": {
   "type": "string"
  },
  "contactName": {
   "type": "string"
  },
  "previousSha256": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true,
  "tool": "extract_page_facts",
  "receipt": {
   "id": "uuid",
   "integrity_sha256": "..."
  },
  "service": "AgentProof"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentproof-extract-page-facts-9fa007a6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentproof.hatchable.site](https://www.zero.xyz/host/agentproof.hatchable.site/llms.txt)