> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/zeroclaw-labs/zeroclaw/llms.txt
> Use this file to discover all available pages before exploring further.

# Browser Tool

> Automated web browsing and scraping

The browser tool enables agents to navigate websites, extract content, and interact with web pages.

## Overview

The browser tool supports:

* Page navigation and content extraction
* JavaScript rendering (optional)
* Screenshot capture
* Form interaction
* Multiple backend modes

## Backends

<Tabs>
  <Tab title="Native (Fantoccini)">
    Uses Rust-native browser automation with WebDriver protocol.

    **Requirements:**

    * ChromeDriver or GeckoDriver running locally
    * Enable with `--features browser-native`

    **Capabilities:**

    * Full JavaScript support
    * Screenshot capture
    * Element interaction
    * Cookie management
  </Tab>

  <Tab title="HTTP (Default)">
    Uses HTTP client for static content extraction.

    **Capabilities:**

    * Fast, lightweight
    * No external dependencies
    * HTML to text conversion
    * No JavaScript execution
  </Tab>
</Tabs>

## Parameters

<ParamField path="url" type="string" required>
  URL to navigate to. Must use http\:// or https\://
</ParamField>

<ParamField path="action" type="string">
  Action to perform: `navigate`, `screenshot`, `click`, `type`
</ParamField>

<ParamField path="selector" type="string">
  CSS selector for element interaction (click/type actions)
</ParamField>

<ParamField path="text" type="string">
  Text to type (for type action)
</ParamField>

## Examples

### Navigate and Extract

```json theme={null}
{
  "url": "https://example.com",
  "action": "navigate"
}
```

### Take Screenshot

```json theme={null}
{
  "url": "https://example.com",
  "action": "screenshot"
}
```

### Fill Form

```json theme={null}
{
  "url": "https://example.com/search",
  "action": "type",
  "selector": "input[name='q']",
  "text": "ZeroClaw framework"
}
```

## Response

<ResponseField name="content" type="string">
  Page content (text or base64-encoded screenshot)
</ResponseField>

<ResponseField name="title" type="string">
  Page title
</ResponseField>

<ResponseField name="url" type="string">
  Final URL after redirects
</ResponseField>

## Configuration

```toml theme={null}
[tools]
browser_enabled = true
browser_backend = "native"  # or "http"
webdriver_url = "http://localhost:9515"

[security]
allowed_domains = [
    "*.github.com",
    "docs.rs",
    "crates.io"
]
```

## Security

<Warning>
  Configure `allowed_domains` to restrict which websites the agent can access.
</Warning>

* Domain allowlist enforcement
* HTTPS preference
* Request timeout (30 seconds)
* Content size limits (5MB)
* User agent identification

## Setup

### Native Backend

<Steps>
  <Step title="Install ChromeDriver">
    ```bash theme={null}
    # macOS
    brew install chromedriver

    # Linux
    wget https://chromedriver.storage.googleapis.com/LATEST_RELEASE
    ```
  </Step>

  <Step title="Start WebDriver">
    ```bash theme={null}
    chromedriver --port=9515
    ```
  </Step>

  <Step title="Build with feature flag">
    ```bash theme={null}
    cargo build --features browser-native
    ```
  </Step>
</Steps>

## Source Code

Implementation: [`src/tools/browser.rs`](https://github.com/zeroclaw-labs/zeroclaw/blob/main/src/tools/browser.rs)

## Related

* [Web Search Tool](/api/tools/web-search)
* [Tool Trait](/api/tool-trait)
* [Security Configuration](/concepts/security)