Agent Browser (Stealth)
Use a hosted browser tuned for tougher web workflows where standard automation is often challenged. Agents get the same governed navigation, screenshots, session persistence, live supervision, and human handoff as Agent Browser, without exposing site credentials to the agent.
Tools
| Name | Description |
|---|---|
snapshotCapture 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_textGet the visible text of the page or a target element. | Get the visible text of the page or a target element. |
read_htmlGet the HTML of the page or a target element. | Get the HTML of the page or a target element. |
screenshotTake 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_stepsRun 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_pageGet the current URL and title. | Get the current URL and title. |
navigateGo to a URL. | Go to a URL. |
navigate_backGo back to the previous page. | Go back to the previous page. |
clickClick an element by ref from snapshot or selector. | Click an element by ref from snapshot or selector. |
typeType 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_formFill 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_optionSelect one or more options in a dropdown. | Select one or more options in a dropdown. |
hoverHover over an element. | Hover over an element. |
dragDrag one element onto another. | Drag one element onto another. |
press_keyPress a keyboard key, such as Enter, Backspace, ArrowDown, or a. | Press a keyboard key, such as Enter, Backspace, ArrowDown, or a. |
file_uploadSet a file on an upload input. | Set a file on an upload input. |
evaluateRun 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_forWait 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_dialogAccept or dismiss a pending JavaScript dialog. | Accept or dismiss a pending JavaScript dialog. |
tabsList, create, close, or select browser tabs. | List, create, close, or select browser tabs. |
show_live_viewMint 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_humanHand 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. |
resumeTake control back from the human and continue automating. | Take control back from the human and continue automating. |
ensure_connectedPreflight 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_statusGet the current handoff state and page. | Get the current handoff state and page. |
start_sessionStart 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_sessionEnd the browser session and snapshot its profile. | End the browser session and snapshot its profile. |
Quick Start
import { WeavzClient } from '@weavz-io/sdk'
const weavz = new WeavzClient({ apiKey: 'wvz_...' })
const result = await weavz.actions.execute('agent-browser-stealth', 'snapshot', {
workspaceId: '550e8400-e29b-41d4-a716-446655440000',
integrationAlias: 'agent-browser-stealth',
input: { /* ... */ },
})Related Integrations
Works well with
Frequently Asked Questions
How do I connect Agent Browser (Stealth) to my app?
Agent Browser (Stealth) does not require an external account connection. Install the SDK, add the integration to a workspace, then execute tools programmatically.
What tools does Agent Browser (Stealth) support?
Agent Browser (Stealth) supports 27 tools including Snapshot Page, Read Text, Read HTML, Screenshot, Run Steps, and more.
Can I use Agent Browser (Stealth) with AI agents?
Yes. Add Agent Browser (Stealth) 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 (Stealth) to ChatGPT or Claude?
Open the Weavz connector setup, sign in, choose a workspace, and add Agent Browser (Stealth) as an approved app. ChatGPT, Claude, and other remote MCP clients can then call the scoped Agent Browser (Stealth) tools exposed by that workspace.
Does Agent Browser (Stealth) 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 (Stealth) work, and execute Code Mode workflows from a terminal.
What can I ask an AI agent to do with Agent Browser (Stealth)?
Agent Browser (Stealth) exposes 27 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 (Stealth) be used in stateful agent workflows?
Yes. Agents can combine Agent Browser (Stealth) 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 (Stealth) use?
Agent Browser (Stealth) does not require external authentication.
How much does the Agent Browser (Stealth) integration cost?
The Agent Browser (Stealth) integration is included on all Weavz plans including the free tier with 20,000 actions per month. No credit card required.
Connect Agent Browser (Stealth) in minutes
Get 20,000 free action executions every month. No credit card required.