Agent Local Browser Control

Agent Local Browser Control

Experimental browser control for a dedicated Chrome profile running on the user machine, so logins use the user network and device.

No AuthExperimentalDeveloper ToolsAI
25 tools

Tools

Name
snapshot

Capture the page accessibility tree with element refs. Read this, then act by ref.

read_text

Get the visible text of the page or a target element.

read_html

Get the HTML of the page or a target element.

screenshot

Take a screenshot of the page or an element. Returns inline image content and a download URL when Filesystem is available.

current_page

Get the current URL and title.

navigate

Go to a URL.

navigate_back

Go back to the previous page.

click

Click an element by ref from snapshot or selector.

type

Type text into an element by ref or selector. Optionally submit with Enter.

fill_form

Fill multiple fields at once. Each field has a target, type, and value.

select_option

Select one or more options in a dropdown.

hover

Hover over an element.

drag

Drag one element onto another.

press_key

Press a keyboard key, such as Enter, Backspace, ArrowDown, or a.

file_upload

Set a file on an upload input.

evaluate

Run a JavaScript function on the page or a target element and return its result.

wait_for

Wait for text to appear/disappear with an optional timeout in seconds. With only time, sleep for that many seconds.

handle_dialog

Accept or dismiss a pending JavaScript dialog.

tabs

List, create, close, or select browser tabs.

request_human

Hand control to a human for login, MFA, or CAPTCHA. Hosted sessions return a viewer URL; local sessions use the local browser window.

resume

Take control back from the human and continue automating.

ensure_connected

Preflight browser readiness. For local browser sessions, briefly waits for the companion and returns whether to proceed, run the command, or start a new session.

session_status

Get the current handoff state and page.

start_session

Start a fresh browser session. Hosted sessions return a viewer link; local sessions return a companion command.

end_session

End the browser session and snapshot its profile.

Quick Start

TypeScript
import { WeavzClient } from '@weavz/sdk'

const weavz = new WeavzClient({ apiKey: 'wvz_...' })

const result = await weavz.actions.execute('agent-local-browser-control', 'snapshot', {
  workspaceId: '550e8400-e29b-41d4-a716-446655440000',
  integrationAlias: 'agent-local-browser-control',
  input: { /* ... */ },
})

Related Integrations

Works well with

Frequently Asked Questions

How do I connect Agent Local Browser Control to my app?

Agent Local Browser Control does not require an external account connection. Install the SDK, add the integration to a workspace, then execute tools programmatically.

What tools does Agent Local Browser Control support?

Agent Local Browser Control supports 25 tools including Snapshot Page, Read Text, Read HTML, Screenshot, Current Page, and more.

Can I use Agent Local Browser Control with AI agents?

Yes. Add Agent Local Browser Control to an MCP server in Tool Mode or Code Mode. Code Mode provides 3 meta-tools with on-demand API discovery so agents can compose stateful workflows without loading every action schema up front.

Can Agent Local Browser Control be used in stateful agent workflows?

Yes. Agents can combine Agent Local Browser Control tools with Filesystem, State KV, Human Gates, input partials, and other workspace integrations while keeping execution scoped to the selected workspace or end user.

What authentication does Agent Local Browser Control use?

Agent Local Browser Control does not require external authentication.

How much does the Agent Local Browser Control integration cost?

The Agent Local Browser Control integration is included on all Weavz plans including the free tier with 20,000 actions per month. No credit card required.

Connect Agent Local Browser Control in minutes

Get 20,000 free action executions every month. No credit card required.