> ## Documentation Index
> Fetch the complete documentation index at: https://docs.riggery.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Read a page

> Read text from a public page.

On the graph, add **Read a page**. On an agent, open **Web** and turn **Read a page** on. Fetches a public page and returns its text. Page scripts are not run.

<h2 id="input">
  Input
</h2>

Inspector **Settings**. Empty-field rules for the Graph: [Previous nodes](/graph/previous-nodes). **Insert value** is on **URL**.

On an Agent Tool, **URL** can be **Agent decides** or **Fixed**. **Max characters** is always your value on the node.

| Field | Required | Empty | Notes |
| - | - | - | - |
| **URL** | Yes | Fail | Public `http` or `https` address. A private-network address is rejected. |
| **Max characters** | No | Default: `8000` | 500–48000. |

A file at this URL fails. Use [Download a file](/graph/tools/web-download).

<h2 id="output">
  Output
</h2>

On the next node, **Previous nodes** lists **`Read a page`: Result** (`{{Read a page.text}}` while the name is unique).

| Output | In menu | Type | Next node gets |
| - | - | - | - |
| Result | Yes | Text | Page text, clipped to **Max characters**. Empty page: `(empty page)`. |