Agent Browser AI

Q: How do I connect Agent Browser AI to my app?

Use Weavz Hosted Connect for custom authentication. Install the SDK, create a connection through the connect portal or API, then execute tools programmatically.

Q: Does Agent Browser AI work with Claude Code, Cursor, Codex, and local agents?

Yes. Remote or local MCP clients can connect to a Weavz MCP endpoint for the workspace. Local coding agents can also use the Weavz CLI to inspect apps, discover actions, and run approved Agent Browser AI work from a terminal.

Q: Can Agent Browser AI be used in stateful agent workflows?

Yes. Weavz lets agents combine Agent Browser AI tools with Filesystem, State KV, Human Gates, input partials, and other workspace integrations while keeping execution scoped to the selected workspace or end user.

Q: What authentication does Agent Browser AI use?

Agent Browser AI uses custom authentication. Weavz stores credentials securely and uses them for authorized action execution.

Give agents goal-level browser instructions instead of step-by-step clicks. Agent Browser AI can act on a task, extract structured page data, and find relevant page elements while preserving governed sessions, human handoff, and user-owned model credentials.

CustomAI Developer Tools

30 tools

Use withChatGPTClaudeClaude CodeCursorCodexMCP clientsSetup guide

Tools

Quick Start

TypeScript

import { WeavzClient } from '@weavz-io/sdk'

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

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

API Reference TypeScript SDK Python SDK All Features Pricing

Related Integrations

1Password

9 tools

Ably

5 tools

Abstract API

5 tools

Adobe Express

5 tools

Works well with

Pike13

67 tools

ServiceM8

61 tools

protocols.io

55 tools

JobNimbus

54 tools

Frequently Asked Questions

How do I connect Agent Browser AI to my app?

Use Weavz Hosted Connect for Custom authentication. Install the SDK, create a connection through the connect portal or API, then execute tools programmatically.

What tools does Agent Browser AI support?

Agent Browser AI supports 30 tools including Snapshot Page, Read Text, Read HTML, Screenshot, Run Steps, and more.

Can I use Agent Browser AI with AI agents?

Yes. Add Agent Browser AI 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.

How do I connect Agent Browser AI to ChatGPT or Claude?

Open the Weavz connector setup, sign in, choose a workspace, and add Agent Browser AI as an approved app. ChatGPT, Claude, and other remote MCP clients can then call the scoped Agent Browser AI tools exposed by that workspace.

Does Agent Browser AI work with Claude Code, Cursor, Codex, and local agents?

Yes. Remote and local MCP clients can connect to a Weavz MCP endpoint for the workspace. Local coding agents can also use the Weavz CLI to inspect apps, discover actions, run approved Agent Browser AI work, and execute Code Mode workflows from a terminal.

What can I ask an AI agent to do with Agent Browser AI?

Agent Browser AI exposes 30 tools, including Snapshot Page, Read Text, Read HTML, Screenshot, Run Steps, and more. Use Weavz to keep credentials scoped, require approval for sensitive work, and audit what the agent did.

Can Agent Browser AI be used in stateful agent workflows?

Yes. Agents can combine Agent Browser AI 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 Browser AI use?

Agent Browser AI uses Custom. Weavz stores credentials securely and uses them for authorized action execution.

How much does the Agent Browser AI integration cost?

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

Connect Agent Browser AI in minutes

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

Get Started Free Browse All Integrations

Name	Description
`snapshot` Capture the page accessibility tree with element refs. Read this, then act by ref.	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.	Get the visible text of the page or a target element.
`read_html` Get the HTML of the page or a target element.	Get the HTML of the page or a target element.
`screenshot` Take a screenshot of the page or an element. Returns inline image content, with an optional Filesystem URL.	Take a screenshot of the page or an element. Returns inline image content, with an optional Filesystem URL.
`run_steps` Run several deterministic browser operations in one session round trip. Use for scripted navigation and extraction flows.	Run several deterministic browser operations in one session round trip. Use for scripted navigation and extraction flows.
`current_page` Get the current URL and title.	Get the current URL and title.
`navigate` Go to a URL.	Go to a URL.
`navigate_back` Go back to the previous page.	Go back to the previous page.
`click` Click an element by ref from snapshot or selector.	Click an element by ref from snapshot or selector.
`type` Type text into an element by ref or selector. Optionally submit with Enter.	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.	Fill multiple fields at once. Each field has a target, type, and value.
`select_option` Select one or more options in a dropdown.	Select one or more options in a dropdown.
`hover` Hover over an element.	Hover over an element.
`drag` Drag one element onto another.	Drag one element onto another.
`press_key` Press a keyboard key, such as Enter, Backspace, ArrowDown, or a.	Press a keyboard key, such as Enter, Backspace, ArrowDown, or a.
`file_upload` Set a file on an upload input.	Set a file on an upload input.
`evaluate` Run a JavaScript function on the page or a target element and return its result.	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.	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.	Accept or dismiss a pending JavaScript dialog.
`tabs` List, create, close, or select browser tabs.	List, create, close, or select browser tabs.
`show_live_view` Mint a watch-only live view URL for the current hosted browser session without handing control away from the agent.	Mint a watch-only live view URL for the current hosted browser session without handing control away from the agent.
`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.	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.	Take control back from the human and continue automating.
`ensure_connected` Preflight browser readiness. For local browser sessions, briefly waits for the extension or companion and returns whether to proceed or recover.	Preflight browser readiness. For local browser sessions, briefly waits for the extension or companion and returns whether to proceed or recover.
`session_status` Get the current handoff state and page.	Get the current handoff state and page.
`start_session` Start a fresh browser session. Hosted sessions return a viewer link; Chrome extension sessions wait for the extension; managed-profile sessions return a companion command.	Start a fresh browser session. Hosted sessions return a viewer link; Chrome extension sessions wait for the extension; managed-profile sessions return a companion command.
`end_session` End the browser session and snapshot its profile.	End the browser session and snapshot its profile.
`act` Use the configured model provider to complete a goal-level browser instruction.	Use the configured model provider to complete a goal-level browser instruction.
`extract` Use the configured model provider to extract structured data from the current page.	Use the configured model provider to extract structured data from the current page.
`observe` Use the configured model provider to identify page elements relevant to an instruction without acting.	Use the configured model provider to identify page elements relevant to an instruction without acting.