# Google-Agent

> Agents hosted on Google infrastructure navigating the web and taking actions on a user's request. Google names one prefix list for it — user-triggered-agents.json — and is separately experimenting with Web Bot Auth under the identity https://agent.bot.goog.

| field | value |
|---|---|
| operator | Google |
| category | User-triggered fetchers |
| robots.txt token | `Google-Agent` |
| user-agent contains | `Google-Agent` |
| robots.txt | not governed by robots.txt (user-initiated, by operator policy) |
| verify by | published IP ranges |
| published IP ranges | https://developers.google.com/static/search/apis/ipranges/user-triggered-agents.json |
| prefixes mirrored | 3 IPv4 / 1 IPv6 |
| operator docs | https://developers.google.com/search/docs/crawling-indexing/google-user-triggered-fetchers |
| last reviewed | 2026-09-01 |

## What blocking it costs you

Google-hosted agents cannot complete a task on your site for a user who asked them to. This is the agentic-commerce fetch: blocking it removes you from what an assistant can actually do rather than from what it can say.

## Full user-agent string

```
Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko; compatible; Google-Agent; +https://developers.google.com/crawling/docs/crawlers-fetchers/google-agent) Chrome/W.X.Y.Z Safari/537.36
```

## Block it

```
User-agent: Google-Agent
Disallow: /
```

## Allow it

```
User-agent: Google-Agent
Allow: /
```

JSON: https://www.pathwren.workers.dev/crawler/google-agent.json · index: https://www.pathwren.workers.dev/llms.txt