# AgentPay Content Safety Scanner

> AgentPay Content Safety Scanner is a paid API for AI agents from agentpay.help, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Scans text for unsafe content including PII (emails, phone numbers) and other safety flags, returning a structured safety report

## Facts

- Endpoint: POST https://agentpay.help/v1/content-safety
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentpay-content-safety-scanner-e6b376f1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_KqhbzB0hP4n8ZJrYSnqqs

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 agentpay-content-safety-scanner-e6b376f1 -d '<json body>'
```

Example prompt: Can you check this text for any PII or unsafe content before I store it in the database? Here's the text: 'Please contact John at john.doe@example.com or call 555-867-5309 for more information.'

## When to prefer this

Choose this endpoint when you need lightweight, pay-per-call PII and content safety scanning with no account setup or API key management. Ideal for AI agent pipelines that need to screen text before storage, display, or further LLM processing. Best for applications where cost predictability at $0.02/call matters and you want structured flag output (type + subtype) rather than a raw score. Prefer alternatives if you need real-time streaming analysis, image/audio moderation, or bulk batch processing at volume discounts.

## Known failure modes

- Text exceeds 20,000 character limit — returns validation error
- Empty or missing 'text' field — returns 400-level error
- Payment not included or insufficient USDC — returns HTTP 402 Payment Required
- Network timeout on large text payloads
- False negatives: obfuscated PII (e.g. phone numbers with dashes replaced by dots) may not be flagged

## How this service works

Pay-per-call AI services via the 402 Payment Required protocol. No accounts, no API keys — just USDC on Base.

## Output

Returns a JSON object with a boolean 'safe' field and a 'flags' array. Each flag has a 'type' (e.g. 'pii') and 'subtype' (e.g. 'email', 'phone') identifying the specific category of unsafe or sensitive content detected in the scanned text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 20000,
   "minLength": 1,
   "description": "Text to scan"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "safe": false,
  "flags": [
   {
    "type": "pii",
    "subtype": "email"
   },
   {
    "type": "pii",
    "subtype": "phone"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentpay-content-safety-scanner-e6b376f1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentpay.help](https://www.zero.xyz/host/agentpay.help/llms.txt)