# Meta-ExternalFetcher

> Meta-ExternalFetcher is dispatched by Meta AI in real time when a user prompt requires retrieving a specific URL — e.g. asking Meta AI to summarise a linked article. Traffic is user-initiated rather than continuous, so robots.txt directives apply per-fetch.

Source: https://docs.centinelanalytica.com/crawlers/meta-externalfetcher

## At a glance

- Operator: [Meta](https://developers.facebook.com/docs/sharing/webmasters/crawler/)
- Type: AI Assistant
- RSL category: `ai-input`

The [bot directory page for Meta-ExternalFetcher](https://www.centinelanalytica.com/bots/meta-externalfetcher) has its robots.txt token and the steps to verify a request from it.

## How Centinel checks it

- **User agent**: The request calls itself this crawler. Anyone can send the same string.
- **IP ranges**: The operator publishes the addresses it crawls from, and Centinel checks the client address against that list.

A request that passes one of these checks is Meta-ExternalFetcher itself. One that only matches the user agent is reported as unverified. The match tokens, verification domains, and address feeds are not published here.

## Allowing or blocking it

The [crawler object](https://docs.centinelanalytica.com/api/crawlers.md) in the `/validate` response sets `access_allowed` to `true` only for a verified source that your tenant allowlists. A [policy rule](https://docs.centinelanalytica.com/admin/policy.md) can allow or block this crawler by its category, `AI Assistant`.

[Back to the crawler catalog](https://docs.centinelanalytica.com/concepts/crawler-catalog.md)

[Crawlers with a source check](https://docs.centinelanalytica.com/crawlers.md)