# Web fetch

Fetch an HTTP/HTTPS URL and return its content. HTML is converted to plain text (or markdown when `format=markdown`). Egress is gated by an SSRF guard that blocks private, loopback, link-local, and metadata-service addresses; redirects are walked manually so the guard re-evaluates every hop.

## What this connection offers

Use the no-sign-in Web fetch tools for accessible web content. No-sign-in does not bypass a site’s login, access restrictions, or unsupported addresses.

| Detail | Value |
| --- | --- |
| Available uses | Assistant tools |
| Sign-in | No sign-in |
| Catalogue identifier | `io.modelcontextprotocol.fetch` |
| Connection scope | tenant |

## Connect

1. Open **Connections**, choose to connect a service, and select **Web fetch** with the uses listed above.
2. Give the connection a recognisable name.
3. Complete creation; no external secret is required for this entry.
4. Check the connection status and run a connection test where offered.
5. Select this saved connection in the app, workflow step, storage browser, or Assistant task that needs it.

## Connection settings

This connector declares no ordinary configuration fields. Its sign-in or managed provisioning flow supplies the access it needs.

## Diagnose a failure

Check the connected account, its permission to the target, the selected folder, table or collection, and the connection’s current status. A successful sign-in is not proof that a particular resource is shared with that account. An empty search or folder page is not necessarily an authentication error. Revoke access when it is no longer needed; deleting the connection can also affect its tools and synced data. See [connection lifecycle](/docs/connections/revoke-and-delete).