# Claude-SearchBot

> Indexes pages so Claude's web search can find and cite them. Separate token from the training crawler, so search visibility and training consent are independent decisions.

| field | value |
|---|---|
| operator | Anthropic |
| category | AI search crawlers |
| robots.txt token | `Claude-SearchBot` |
| user-agent contains | `Claude-SearchBot` |
| robots.txt | obeys robots.txt (documented) |
| verify by | no published verification method |
| published IP ranges | none published |
| prefixes mirrored | 0 IPv4 / 0 IPv6 |
| operator docs | https://support.anthropic.com/en/articles/8896518 |
| last reviewed | 2026-09-01 |

## What blocking it costs you

You stop appearing in Claude's search results and citations.

## Full user-agent string

```
Mozilla/5.0 (compatible; Claude-SearchBot/1.0; +Claude-SearchBot@anthropic.com)
```

## Block it

```
User-agent: Claude-SearchBot
Disallow: /
```

## Allow it

```
User-agent: Claude-SearchBot
Allow: /
```

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