Skip to main content
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

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

Parameters

string
required
URL to navigate to. Must use http:// or https://
string
Action to perform: navigate, screenshot, click, type
string
CSS selector for element interaction (click/type actions)
string
Text to type (for type action)

Examples

Take Screenshot

Fill Form

Response

string
Page content (text or base64-encoded screenshot)
string
Page title
string
Final URL after redirects

Configuration

Security

Configure allowed_domains to restrict which websites the agent can access.
  • Domain allowlist enforcement
  • HTTPS preference
  • Request timeout (30 seconds)
  • Content size limits (5MB)
  • User agent identification

Setup

Native Backend

1

Install ChromeDriver

2

Start WebDriver

3

Build with feature flag

Source Code

Implementation: src/tools/browser.rs