Navigate to a URL. Returns {url, title} by default (lean). Set snapshot=true for full accessibility tree + screenshot (expensive — use only when you need to discover page structure).

Take a snapshot of the current page. Returns accessibility tree (numbered elements). Set lite=true to skip the screenshot (saves ~50K+ tokens). Use full snapshot only when you need to visually see the page.

Get the current page's accessibility tree (numbered elements) without taking a screenshot. Faster than scout_snapshot.

Take a plain screenshot of the current page without element badges.

Click an element by its snapshot ID. Returns healer result describing what changed. If stateChange is 'navigation', element IDs are now stale — call scout_snapshot before using any IDs again. Use force=true to bypass overlay elements (shadow DOM, modals) that intercept clicks.

Type text into an input element by its snapshot ID. Uses React-safe keyboard events. If stateChange is 'navigation', call scout_snapshot before using any IDs again.

Scroll the page or a specific element (modal, dialog) in a direction. Use element_id to scroll within a container instead of the whole page.

Select an option from a dropdown/select element by its snapshot ID.

Wait for a page condition.

Hover over an element by its snapshot ID.

Press a keyboard key (e.g. Enter, Escape, ArrowDown, Backspace).

Go back in browser history.

Go forward in browser history.

Refresh the current page.

Block certain resource types to speed up loading (e.g. image, media, stylesheet, font, script).

Drag one element onto another.

Save the current browser session (cookies, localStorage) to a named file.

Load a saved browser session. This will restart the browser context.

List all saved browser sessions.

Get the last 100 browser console logs and errors.

Execute JavaScript in the current page and return the result. Use for: reading page state, clicking elements blocked by shadow DOM overlays, interacting with Web Components, or any DOM operation not covered by other tools. The code runs in the page context with full DOM access. Returns the serialized result.

Inject a banner in the live browser asking the user to take a manual action. Returns IMMEDIATELY with a handoff_id — does NOT block. Poll scout_handoff_check(handoff_id) every 5-10 seconds until status is 'completed'. Use for: CAPTCHAs, SMS codes, authenticator app prompts, email verification.

Check whether a pending handoff has been completed by the human. Returns immediately. Call this every 5-10 seconds after scout_handoff until status is 'completed' or 'expired'.

Cancel a pending handoff and remove the banner from the browser.

List all open browser tabs with their index, URL, title, and which is active.

Switch to a browser tab by index (from scout_tabs).

Open a new browser tab, optionally navigating to a URL.

Compose and publish a post on a social platform (linkedin, x, medium). Uses the platform adapter pattern — handles shadow DOM, selectors, and compose flows automatically. The browser must be logged into the platform.

Get your recent posts on a platform.

Delete one of your posts on a platform.

Search for posts on a platform.