# Agent Newsstand — URL Safety Check

> Agent Newsstand — URL Safety Check is a paid API for AI agents from api.agentnewsstand.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Checks whether a given URL is safe or malicious before an AI agent visits it

## Facts

- Endpoint: GET https://api.agentnewsstand.com/v1/url/safety
- 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-newsstand-url-safety-check-a618108d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_62g24iR5VX9zcoRUCep6r

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-newsstand-url-safety-check-a618108d
```

Example prompt: Before you scrape that page, can you check whether https://suspicious-site.xyz/offer is actually safe to visit or if it looks like phishing or malware?

## When to prefer this

Use this endpoint when an AI agent needs to vet a user-submitted or discovered URL before visiting, scraping, or sharing it — especially in pipelines where untrusted URLs from emails, search results, or user input must be screened. Prefer this over a generic web search for explicit threat-classification signals rather than general reputation.

## Known failure modes

- Invalid or malformed URL returns a validation error
- URL that resolves to a redirect chain may only assess the initial URL
- Unknown or brand-new domains may lack threat intelligence data, returning inconclusive results
- Rate limiting or payment failure results in 402 or 429 response
- Network timeouts if the safety lookup backend is slow

## How this service works

15 pay-per-call endpoints for AI agents: tokenized-asset candles, SEC filings, earnings, US macro, web search, page reader, paywall unlock, screenshots. USDC on Base via x402. No API keys, no signup.

## Output

Returns a safety assessment for the submitted URL, indicating whether it is safe, suspicious, malicious, or phishing, along with any relevant threat classification details.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "format": "uri"
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-newsstand-url-safety-check-a618108d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentnewsstand.com](https://www.zero.xyz/host/api.agentnewsstand.com/llms.txt)