Scout connector docs

List all available browser tabs with their titles, URLs, and tab IDs. Returns @t refs for use with browser-attach.

Attach a CDP session to a specific browser tab and create a session ID (@x ref). Required before most browser operations.

Detach a CDP session from a tab and clean up all associated state. Always call when done with a tab.

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

Launch Chromium with a persistent user-data directory. Preserves cookies, extensions, and login state across restarts.

Close a browser tab and clean up its session. The tab is removed from the browser.

Connect to an externally launched Chromium instance through its remote-debugging domain and port.

Disconnect from an externally connected browser instance.

List all active sessions managed by the current Scout instance. Shows session IDs, tab refs, URLs, and titles.

Send a message to a peer agent controlling a different tab. Used for multi-agent coordination.

List all peer agents currently active in the Scout session. Returns agent refs, their tab assignments, and session IDs.

Submit a request to a peer agent and await its response. Synchronous cross-agent RPC.

Reply to a pending agent-request. Used by specialized agents to respond to orchestrator requests.

Navigate to a URL, reload, go back/forward, or set page HTML directly. Waits for the page to load before returning.

Perform a web search using any of 17 supported engines.

List or clear the session's browser navigation history.

Capture a still image from a video element at a specific timestamp. Auto-detects the first <video> if no selector is given.

List all iframes on the current page with their source URLs and @ref identifiers.

Wait for a specific condition before proceeding. Supports page load states, selector matching, text matching, URL matching, response matching, or a fixed delay. When more than one page scope is in play, tabRef determines which page the wait observes.

Capture the accessibility tree of the current page as a structured snapshot. Returns @e refs for all interactive elements. The primary tool for page observation. When more than one page scope is in play, tabRef determines which page the returned refs belong to.

Extract data from the DOM. Supports property types: article (clean markdown via Readability), text, html, markdown, value, attribute, title, url, count, box, visible, enabled, checked, focused. Use @ref or CSS selector for element properties.

Execute JavaScript in the page context. Returns the evaluated result. Supports async expressions.

Evaluate JavaScript and write the result directly to a file on disk. Use for large datasets that would exceed context limits.

Search for text within the page using the browser's find bar. Returns match count and scrolls to the first match.

Inject a script or stylesheet into the page. Supports inline content, external URL, or init scripts that run on every navigation.

Discover available Scout tools with optional category filter and detail level. Used for progressive tool loading by agents.

Perform a user interaction on a page element. Supports 16 action types including touch tap with coordinate support. @e refs from browser-snapshot and CSS selectors are both supported. When more than one page scope is in play, tabRef determines which page the action and any @e refs are scoped to.

Select one or more options from a <select> element or a custom dropdown.

Upload one or more files to a file input element.

Handle a browser dialog (alert, confirm, prompt, beforeunload). Accept or dismiss with optional input text.

Highlight one or more elements visually. Adds colored border/overlay for debugging or visual confirmation. Supports label, style, and auto-timeout.

List, get, or clear captured network requests. Tracks requests with status, headers, timing, and body.

Intercept and handle network requests matching a URL pattern. Supports logging, blocking, or modifying responses.

Remove a previously registered request interception route.

Start or stop recording network traffic as an HTTP Archive (HAR) file.

Control SSL certificate error handling. Set ignore=true for self-signed certificates in testing environments.

Drain the notification queue for network events, console logs, dialogs, and other asynchronous browser events.

Send a desktop notification to the user through the browser. Useful for signaling task completion.

Track WebSocket connections and their messages. Actions: list, get, clear.

Get, set, or clear browser cookies for the current session.

Interact with localStorage or sessionStorage.

Read from or write to the system clipboard.

Capture a screenshot of the viewport, full page, a specific element, or an arbitrary region. When more than one page scope is in play, tabRef determines which page the capture targets. Annotated @e refs belong to the tab that produced the corresponding snapshot.

Generate a PDF of the current page.

Start or stop a screen recording session. Returns video data on stop.

Capture a video frame at a specific timestamp, or extract audio from a media element.

List, get, or clear browser downloads. Track in-progress and recently completed downloads.

Transcribe speech from an audio/video element using AI. Returns a time-stamped transcript.

Capture or drain browser console logs. Returns entries with type, message, and timestamp. Types: log, info, warning, error.

Get page performance metrics: load time, first paint, FCP, DOM interactive, DOM content loaded.

Get DOM memory counters: document count, node count, JS event listener count. Useful for detecting memory leaks.

Connect to an existing Chrome or Chromium remote-debugging endpoint and bind the session to a live page by supplying its domain and port.

Emulate browser environment — user agent, color scheme, locale, geolocation, timezone, media type, and more.

Resize the browser viewport to specific dimensions. Use for responsive design testing.

Simulate a vision deficiency for accessibility testing: color blindness, blurred vision, reduced contrast.

Throttle the CPU to simulate slow devices. Multiply by 4 for a mid-range mobile device.

Throttle network speed to simulate different connection conditions.

Simulate touch gestures: pinch to zoom, momentum scroll, or finger tap at specific coordinates.

Execute multiple tool calls in a single request. Reduces round-trip overhead for sequential operations. Returns an array of results.

Execute a multi-step browser workflow with conditional branching. Steps can be actions (tool calls) or conditions (with then/else branches).

Crawl multiple URLs in parallel with optional link discovery, fingerprinting, session pooling, and resource blocking.

Execute a high-level natural language browser task. Scout determines the steps needed and executes them autonomously.

Establish a persistent channel between an agent and a browser tab for bidirectional communication.

Animate an element on the page using the Web Animations API.

Get computed CSS styles for an element. Returns final rendered values after the full cascade.

Scroll the page or a specific element.

Check the current wallet balance. Returns the wallet address, selected asset balance, and asset metadata. Scout uses the wallet authority already attached to the active agent run, and also accepts an optional walletPrivateKey override for direct callers.

Fetch a payment-gated resource. Automatically negotiates explicit x402 or MPP payment challenges when the server returns a 402 Payment Required response. Handles the full payment flow: detect 402, apply hard x402 policy constraints when relevant, sign payment, and retry with payment proof.

Transfer the selected wallet-backed asset to another EVM-compatible wallet address. Executes an on-chain transfer using the configured wallet.