# AI Crawler Access Watch

> AI Crawler Access Watch is a paid API for AI agents from tizona-outpost.venusberg.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Register a standing watch over a list of URLs to monitor how sites treat AI crawlers (GPTBot, ClaudeBot, etc.) and pull changes on demand using pre-bought credits.

## Facts

- Endpoint: POST https://tizona-outpost.venusberg.workers.dev/v1/watch/register
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ai-crawler-access-watch-389cc959
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WUN9FBEr76xUU7KdA-bmr

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 ai-crawler-access-watch-389cc959 -d '<json body>'
```

Example prompt: Set up a standing watch on these 5 URLs — https://example.com, https://news-site.com, https://shop.com, https://blog.example.org, https://forum.site.net — with 10 pull credits, so I can track whether they start blocking or allowing AI crawlers like GPTBot and ClaudeBot over time.

## When to prefer this

Choose this endpoint when you need ongoing, asynchronous monitoring of AI crawler policies across multiple URLs rather than a one-shot bulk check. It is preferable over the sibling triage endpoint when you need persistent tracking with change deltas over days or weeks, and when pre-buying pull credits is more efficient than paying per triage call. Ideal for agents running scheduled compliance audits, competitive intelligence pipelines, or LLM training data sourcing workflows.

## Known failure modes

- Invalid or malformed URLs in the array — returns validation error
- Insufficient credits value (zero or negative) — rejected at registration
- watchId not found or expired on pull — watch may have lapsed after 30 days of inactivity
- Rate limiting or payment failure — x402 payment required per call
- Empty URL list — endpoint may reject or return no-op response

## How this service works

Register a standing watch over a set of URLs and pre-buy pull credits. POST {"urls":[...],"credits":10}; we keep those URLs in the AI-crawler-access census. Pull with POST /v1/watch/pull {"watchId":...} to get what changed since your last pull. Watches expire after 30 days unless refreshed by activity. For agents that need ongoing monitoring of whether sites serve, refuse, or tollgate AI crawlers like GPTBot and ClaudeBot.

## Output

Returns a watchId that identifies the registered watch session. Subsequent pulls via /v1/watch/pull with that watchId return a delta of what changed in AI crawler access status (served, refused, or tollgated) for each monitored URL since the last pull. Watches remain active for 30 days, refreshed by activity.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   }
  },
  "credits": {
   "type": "integer"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ai-crawler-access-watch-389cc959/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tizona-outpost.venusberg.workers.dev](https://www.zero.xyz/host/tizona-outpost.venusberg.workers.dev/llms.txt)