BrowseAgent

Drives a real browser: navigate, click, screenshot. For what only appears after JavaScript, or behind a login.

Connecting

In the dashboard, open Connectors, find BrowseAgent and press Connect. The key you enter is checked against BrowseAgent before anything is saved, so a key that is refused never becomes a connection that fails later.

Getting the credential

Install Chrome Extension: Install the BrowseAgent Chrome Extension from the Chrome Web Store.
Connect & Use
- Open the extension popup and click “Connect” and copy the BrowseAgent mcp server extension bridge url and use for the extension bridge endpoint.
- Start automating - try saying: “Take a screenshot of google.com”
That’s it! 🎉

Notes

This one drives a browser through the BoostGPT extension rather than calling an API, so the extension has to be installed and the tab open. Nothing happens server-side.

What an agent can do with it

Tool	What it does
`browser_navigate`	Navigate to a URL in a new or existing tab
`browser_go_back`	Go back to the previous page
`browser_go_forward`	Go forward to the next page
`browser_wait`	Wait for a specified time in seconds
`browser_press_key`	Press a key on the keyboard
`browser_snapshot`	Capture accessibility snapshot of the current page. Use this for getting references to elements to interact with.
`browser_click`	Perform click on a web page
`browser_drag_drop`	Perform drag and drop between two elements
`browser_hover`	Hover over element on page
`browser_type`	Type text into editable element
`browser_get_console_logs`	Get the console logs from the browser
`browser_screenshot`	Take a screenshot of the current page

Getting Started

Choose Your Path

Providers & Models

Connecting

Getting the credential

Notes

What an agent can do with it

​Connecting

​Getting the credential

​Notes

​What an agent can do with it

Connecting

Getting the credential

Notes

What an agent can do with it