Documentation

Scout docs

Connect an agent, make your first call, and find the reference you need.

Tool reference

Tool reference

Find a tool, inspect its parameters, and check what it returns.

https://mcp.scout.i.ng/browser

63 tools · Browser connector guide

Session
9

Manage browser sessions, tab attachment, and multi-agent coordination.

browser-tabs

List all available browser tabs with their titles, URLs, and tab IDs. Returns @t refs used to scope subsequent tab operations.

No parameters.

Returns: Array of tab objects with @t refs, titles, and URLs

browser-detach

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

No parameters.

Returns: Confirmation of detachment

browser-launch

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

ParameterTypeDescription
url

Optional

stringURL to open in the new tab

Default: about:blank

Returns: @t ref for the new tab

browser-open

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

ParameterTypeDescription
userDataDir

Required

stringPersistent browser profile directory path
url

Optional

stringURL to navigate to after opening the profile

Default: about:blank

Returns: Session ID with persistent profile context

browser-close

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

No parameters.

Returns: Confirmation of closure

browser-connect

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

ParameterTypeDescription
domain

Optional

stringHostname that exposes the browser remote-debugging listener, as seen from the machine the Scout server runs on. Defaults to 127.0.0.1.
port

Optional

numberRemote-debugging port. Defaults to 9222.

Returns: Connection ID and available tab refs

browser-disconnect

Disconnect from an externally connected browser instance.

No parameters.

Returns: Confirmation of disconnection

browser-remote

Connect to a remote Playwright browser server via WebSocket, create a tracked MCP session, and bind to an initial active page.

ParameterTypeDescription
wsEndpoint

Required

stringPlaywright browser server WebSocket endpoint to connect to (e.g., ws://127.0.0.1:3000/<token>).
timeout

Optional

numberTimeout in milliseconds for the connection attempt

Default: 30000

maxConsoleLogs

Optional

numberMaximum number of console logs to track

Default: 100

maxNetworkRequests

Optional

numberMaximum number of network requests to track

Default: 100

maxWebSocketConnections

Optional

numberMaximum number of WebSocket connections to track

Default: 50

captureBodyPattern

Optional

stringGlob pattern for response body capture (e.g., '**/api/**'). Matching responses store their body up to 5 MB.

Returns: Tracked session bound to the remote browser's active page

browser-session

List, inspect, or close connector-owned browser sessions managed by the current Scout instance.

ParameterTypeDescription
action

Required

'list' | 'status' | 'close'Action: list, status (inspect one session), or close
connectionId

Optional

stringRemote browser connection ID that owns the tab (for status/close).
tabId

Optional

numberTab identifier within the remote browser connection (for status/close).
drainNotifications

Optional

booleanDrain pending notifications when inspecting a session (status action).

Default: false

Returns: Session list, status details, or closure confirmation

Navigation
6

Navigate between pages, manage browser history, and handle iframes.

browser-navigate

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

ParameterTypeDescription
action

Required

stringNavigation action: goto (navigate to URL), reload, back, forward, setcontent (set page HTML)
url

Optional

stringURL to navigate to (required for 'goto' action)
waitUntil

Optional

stringWhen to consider navigation complete. Options: load, domcontentloaded, networkidle, commit

Default: load

html

Optional

stringHTML content to set (required for 'setcontent' action)

Returns: Page title and final URL after navigation

browser-search

Perform a web search using any of 17 supported engines.

ParameterTypeDescription
query

Required

stringSearch query text
engine

Required

stringSearch engine: google, duckduckgo, bing, brave, yahoo, yandex, startpage, and more. duckduckgo recommended (fewer captchas).

Returns: Snapshot of the search results page

browser-history

List or clear the session's browser navigation history.

ParameterTypeDescription
action

Required

'list' | 'clear'History action: list (show navigation history) or clear (reset history)

Returns: Navigation history entries or confirmation

browser-scene

Save and restore named scenes — the current page URL, title, and scroll position — within a session.

ParameterTypeDescription
action

Required

'capture' | 'restore' | 'list' | 'delete'Action: capture (save current page as a named scene), restore (navigate back to a scene), list, or delete
name

Optional

stringUnique scene name within the session
scroll

Optional

booleanWhether to restore the scroll position in addition to the URL (restore action)

Default: true

Returns: Scene list or navigation confirmation

browser-frames

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

No parameters.

Returns: Array of iframe metadata

browser-wait

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.

ParameterTypeDescription
type

Required

stringWait type: load, delay, selector, text, url, or response
selectors

Optional

string[]CSS selectors to try when type='selector'. The wait succeeds when any selector resolves.
matchers

Optional

Array<{ matchType: 'text' | 'glob' | 'regex'; value: string }>Matchers to try when type='text', 'url', or 'response'. Each matcher provides its own matchType ('text', 'glob', or 'regex') and value.
state

Optional

stringLoad state to wait for when type='load': load, domcontentloaded, or networkidle.
delayMs

Optional

numberHow long to pause in milliseconds when type='delay'.
tabRef

Optional

stringTab ref that scopes the wait to a specific page. When omitted, the active tab is targeted.
timeout

Optional

numberMaximum time to wait in milliseconds.

Returns: Confirmation when condition is met

Content
9

Read and understand page content — snapshots, extraction, JavaScript evaluation.

browser-snapshot

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.

ParameterTypeDescription
tabRef

Optional

stringTab ref that scopes the snapshot to a specific page. When omitted, the active tab is targeted. Returned @e refs belong to that tab.
selector

Optional

stringCSS selector to scope the snapshot to a specific element region
deduplicate

Optional

booleanCollapse identical repeated subtrees with a ×N indicator
disambiguate

Optional

booleanAdd [in=section] ancestor context to duplicate interactive elements
excludeDecorative

Optional

booleanRemove decorative elements (unlabeled images, aria-hidden, empty buttons)
excludeRoles

Optional

string[]Roles to exclude from the snapshot (e.g., ['separator', 'presentation'])
includeRoles

Optional

string[]Only include these roles — whitelist mode (e.g., ['link', 'button'])
maxDepth

Optional

numberMaximum tree depth to include
maxElements

Optional

numberMaximum number of elements. Use selector to narrow scope instead.
viewportOnly

Optional

booleanOnly include elements in the current viewport
flattenBeyondDepth

Optional

numberCollapse non-interactive nodes beyond this depth, promoting interactive children
groupCodeBlocks

Optional

booleanMerge sequential code lines into compact labeled blocks

Returns: YAML accessibility tree with @e refs, roles, labels, and values

browser-element

Inspect a targeted element by @ref or selector and return one semantic detail: position, size, visibility, content, attributes, styles, accessibility, state, value, or a fused layout summary.

ParameterTypeDescription
detail

Required

'position' | 'size' | 'visibility' | 'content' | 'attributes' | 'styles' | 'accessibility' | 'state' | 'value' | 'layout'Semantic detail to return: position, size, visibility, content, attributes, styles, accessibility, state, value, or layout
selector

Optional

stringElement selector: @ref (e.g., @e1) from snapshot, or CSS selector

Returns: One semantic detail object for the targeted element

browser-extract

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

ParameterTypeDescription
property

Required

stringWhat property to retrieve: article, text, html, markdown, value, attribute, title, url, count, box, visible, enabled, checked, focused
selector

Optional

stringElement selector: @ref (e.g., @e1) from snapshot, or CSS selector. Required for element properties.
attribute

Optional

stringAttribute name to get (only for 'attribute' property)

Returns: Extracted property value from the DOM

browser-evaluate

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

ParameterTypeDescription
expression

Required

stringJavaScript expression to evaluate

Returns: JSON-serializable result of the expression

browser-pipe

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

ParameterTypeDescription
expression

Required

stringJavaScript expression to evaluate
filePath

Required

stringAbsolute file path to write to
format

Optional

stringOutput format: json, yaml, text, or base64

Default: json

append

Optional

booleanAppend to file instead of overwriting

Default: false

Returns: Confirmation with byte count and file path

browser-find

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

ParameterTypeDescription
text

Required

stringText to find on the page
index

Optional

numberWhich match to scroll to (0-based)

Default: 0

Returns: Match count and current match index

browser-inject

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

ParameterTypeDescription
type

Required

'script' | 'style' | 'initscript'Type: script, style, or initscript (runs on every navigation)
content

Optional

stringInline content to inject
url

Optional

stringURL to inject from

Returns: Confirmation of injection

browser-file

Inspect or clear the session's tracked file references (@o refs) used for uploads and other file-backed actions.

ParameterTypeDescription
action

Required

'list' | 'get' | 'clear'Action: list (tracked files), get (one file ref), or clear (reset the registry)
fileRef

Optional

stringFile ref to inspect (get action)
pattern

Optional

stringFilter pattern for file path or name matching (list action)

Returns: Tracked file references or confirmation

browser-source

Capture browser-readable source from the current page — full HTML, stylesheet/script sources, image asset metadata, or a specific resource URL.

ParameterTypeDescription
kind

Required

'document' | 'styles' | 'scripts' | 'images' | 'resource'What to capture: document, styles, scripts, images, or resource (a specific URL)
sessionRef

Required

stringSession ID
url

Optional

stringAbsolute resource URL to fetch when kind='resource'
includeContent

Optional

booleanInclude inline HTML, stylesheet text, script text, or fetched resource bodies when the runtime can access them

Default: true

maxItems

Optional

numberMaximum number of stylesheets, scripts, or images to include in list-based captures

Default: 25

timeout

Optional

numberMaximum time in milliseconds to wait for the source capture to complete

Default: 30000

Returns: Captured document HTML, resource sources, or asset metadata

Interaction
4

Simulate user interactions — clicks, keyboard input, form filling, drag-and-drop.

browser-interact

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.

ParameterTypeDescription
action

Required

stringAction type: click, clear, dblclick, drag, fill, focus, highlight, hover, check, press, scroll, select, tap, type, uncheck
selector

Required

stringElement selector: @ref from snapshot (preferred) or CSS selector
tabRef

Optional

stringTab ref that scopes the action to a specific page. When omitted, the active tab is targeted. @e refs belong to the tab that produced the snapshot.
value

Optional

stringValue for fill, type, or select actions
key

Optional

stringKey to press (e.g., Enter, Tab, Control+a)
button

Optional

'left' | 'right' | 'middle'Mouse button for click actions

Default: left

force

Optional

booleanBypass actionability checks. Use when overlays intercept clicks.

Default: false

timeout

Optional

numberMaximum wait time in milliseconds

Default: 5000

targetSelector

Optional

stringTarget selector for drag actions (required for drag only)
direction

Optional

'up' | 'down' | 'left' | 'right'Scroll direction for scroll actions

Default: down

pixels

Optional

numberPixels to scroll

Default: 500

position

Optional

{ x: number, y: number }Coordinates for tap action: { x, y }. Taps at these coordinates instead of element center.
tapCount

Optional

numberNumber of taps to perform (tap action only)

Default: 1

Returns: Updated accessibility snapshot reflecting the new page state

browser-attach

Attach one or more files to a file input element.

ParameterTypeDescription
selector

Required

string@ref or CSS selector of the file input
files

Required

string[]Absolute file paths to attach

Returns: Confirmation of file attachment

browser-dialog

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

ParameterTypeDescription
action

Required

'accept' | 'dismiss'Dialog ref (@g ref) or action: accept, dismiss
promptText

Optional

stringText to enter for prompt dialogs

Returns: Confirmation of dialog handling

browser-highlight

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

ParameterTypeDescription
action

Required

'show' | 'hide' | 'clear' | 'pulse'Action: show (add highlight), hide (remove), clear (remove all), pulse (animate)
selector

Optional

stringCSS selector or @ref (required for show/hide/pulse)
style

Optional

stringVisual style: border, overlay, spotlight, crosshair

Default: border

color

Optional

stringHighlight color: red, blue, green, yellow, orange, purple, cyan

Default: cyan

label

Optional

stringLabel to display near the element
duration

Optional

numberAuto-remove timeout in milliseconds

Default: 1000

Returns: Confirmation

Network
7

Monitor network traffic, intercept requests, record HAR files, manage certificates.

browser-network

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

ParameterTypeDescription
action

Required

'list' | 'get' | 'clear'Action: list, get (@n ref), clear
pattern

Optional

stringFilter by URL pattern (glob supported). Used with list.
requestRef

Optional

stringNetwork request ref (@n1) for get action

Returns: Array of network request objects or a single request detail

browser-route

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

ParameterTypeDescription
pattern

Required

stringURL pattern to intercept (glob or regex, e.g., **/api/v2/**)
action

Required

'abort' | 'fulfill' | 'continue'What to do with matched requests: abort (block), fulfill (return custom response), continue (proceed with optional modifications)
responseBody

Optional

stringMock response body for modify action
responseStatus

Optional

numberMock response status for modify action

Returns: Confirmation of route registration

browser-unroute

Remove a previously registered request interception route.

ParameterTypeDescription
pattern

Required

stringURL pattern to remove interception for

Returns: Confirmation

browser-har

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

ParameterTypeDescription
action

Required

'start' | 'stop'Action: start or stop recording
filePath

Optional

stringFile path to save the HAR file to (required for stop)

Returns: HAR data or confirmation of start/stop

browser-security

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

ParameterTypeDescription
ignore

Required

booleanWhether to ignore certificate errors

Returns: Confirmation

browser-notifications

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

No parameters.

Returns: Array of pending events with type, timestamp, and data

browser-websocket

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

ParameterTypeDescription
action

Required

'list' | 'get' | 'clear'Action: list (all connections), get (by ref), clear
webSocketId

Optional

stringWebSocket ref (@w1) for get action
pattern

Optional

stringURL pattern filter for list action

Returns: WebSocket connections or message history

Storage
4

Manage cookies, localStorage, sessionStorage, and clipboard.

browser-cookies

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

ParameterTypeDescription
action

Required

'get' | 'set' | 'clear'Cookie operation: get, set, or clear
cookies

Optional

CookieObject[]Array of cookie objects to set (required for set action). Each cookie has name, value, and optional domain, path, httpOnly, secure, sameSite, expires, url.

Returns: Cookie value(s) or confirmation

browser-storage

Interact with localStorage or sessionStorage.

ParameterTypeDescription
action

Required

'get' | 'set' | 'remove' | 'clear' | 'keys'Action: get (retrieve value), set (store value), remove (delete key), clear (remove all), keys (list all keys)
storageType

Optional

'local' | 'session'Storage type: 'local' for localStorage, 'session' for sessionStorage

Default: local

key

Optional

stringStorage key (required for get, set, remove)
value

Optional

stringValue to store (required for set)

Returns: Storage value, key list, or confirmation

browser-clipboard

Read from or write to the system clipboard.

ParameterTypeDescription
action

Required

'read' | 'write'Action: read or write
text

Optional

stringText to write to clipboard (write only)

Returns: Clipboard text (read) or confirmation (write)

browser-bookmarks

Manage browser bookmarks — list a folder, read the tree, search, and create, update, move, or remove bookmarks and folders.

ParameterTypeDescription
action

Required

'list' | 'tree' | 'search' | 'get' | 'create' | 'update' | 'move' | 'remove'Action: list, tree, search, get, create, update, move, or remove
title

Optional

stringBookmark or folder title (create/update actions)
url

Optional

stringBookmark URL for bookmark creation. When omitted, the operation creates a folder.
parentId

Optional

stringParent folder ID. Defaults to the root folder (create action).
bookmarkId

Optional

stringBookmark node identifier (get/update/move/remove)
query

Optional

stringSearch text for bookmark lookup (search action)
index

Optional

numberOptional position within the parent folder (create action)

Returns: Bookmark list, tree, search results, or operation confirmation

Media
8

Capture screenshots, record screencasts, manage downloads, control media playback.

browser-screenshot

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.

ParameterTypeDescription
target

Required

'screen' | 'page' | 'element' | 'clip'Capture target: screen (viewport), page (full document), element (DOM element), clip (arbitrary rectangle)
tabRef

Optional

stringTab ref that scopes the capture to a specific page. When omitted, the active tab is targeted. Annotated @e refs belong to the tab that produced the snapshot.
format

Optional

'jpeg' | 'png'Image format: jpeg (smaller, lossy) or png (larger, lossless)

Default: jpeg

selector

Optional

stringElement selector: @ref or CSS selector (required for 'element' target)
x

Optional

numberClip x-coordinate in pixels (required for 'clip' target)
y

Optional

numberClip y-coordinate in pixels (required for 'clip' target)
width

Optional

numberClip width in pixels (required for 'clip' target)
height

Optional

numberClip height in pixels (required for 'clip' target)
annotate

Optional

booleanOverlay @eN ref labels on interactive elements before capture

Default: false

Returns: Base64-encoded image

browser-pdf

Generate a PDF of the current page.

ParameterTypeDescription
format

Optional

stringPaper format: A4, Letter, Legal, Tabloid, A3, A5, A6

Default: A4

landscape

Optional

booleanLandscape orientation

Default: false

printBackground

Optional

booleanInclude background graphics

Default: false

pageRanges

Optional

stringPage range (e.g., '1-5, 8')

Returns: Base64-encoded PDF

browser-screencast

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

ParameterTypeDescription
action

Required

'start' | 'stop'Action: start or stop
filePath

Optional

stringFile path to save the recording to

Returns: Confirmation (start) or video file path (stop)

browser-media

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

ParameterTypeDescription
selector

Required

string@ref or CSS selector of the media element
action

Required

'frame' | 'audio'Action: frame (video) or audio
timestamp

Optional

numberTimestamp in seconds for frame capture

Returns: Base64-encoded frame image or audio data

browser-download

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

ParameterTypeDescription
action

Required

'list' | 'get' | 'clear'Action: list, get (@d ref), clear
downloadId

Optional

stringDownload ref (@d1) for get action

Returns: Download object(s) with status, URL, and file path

browser-transcribe

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

ParameterTypeDescription
selector

Required

string@ref or CSS selector of the media element

Returns: Transcript with timestamps and speaker segments

browser-still

Capture a still image from a video or media element at a specific playback timestamp. Auto-detects the first <video> element when no ref is given.

ParameterTypeDescription
elementRef

Optional

stringSnapshot video ref. Defaults to the first <video> element in the targeted page.
format

Optional

'jpeg' | 'png'Image format for the captured frame

Default: jpeg

quality

Optional

numberImage quality (0-100, JPEG only)
time

Required

numberTimestamp in seconds to seek to before capturing the frame

Returns: Base64-encoded still frame image

browser-image

Read a snapshot-issued image ref (@i) and return the rendered image as a PNG or JPEG image resource.

ParameterTypeDescription
imageRef

Required

stringSnapshot image ref (e.g., @i12). Image refs come from browser-snapshot and are separate from actionable @e refs.
format

Required

'png' | 'jpeg'Image format: png (lossless) or jpeg (smaller, quality adjustable)
quality

Optional

numberImage quality (0-100) for JPEG output

Default: 80

Returns: PNG or JPEG image resource

Debug
6

Inspect console output, measure performance, monitor DOM memory stats.

browser-console

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

ParameterTypeDescription
action

Required

'enable' | 'drain'Action: enable (start capture), drain (get + clear)
type

Optional

stringFilter by type: log, info, warning, error, all

Returns: Array of console log entries

browser-metrics

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

No parameters.

Returns: Performance timing object with all Navigation Timing metrics

browser-memory

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

No parameters.

Returns: Memory statistics object

browser-exceptions

List, get, summarize, or clear uncaught page exceptions captured for a browser session.

ParameterTypeDescription
action

Required

'list' | 'get' | 'summarize' | 'clear'Action: list, get (by ref), summarize, or clear
exceptionRef

Optional

stringException ref to retrieve (get action)
limit

Optional

numberMaximum number of exceptions to return (list action). Reduces token usage for large buffers.
pattern

Optional

stringText pattern to filter exception messages. Plain text does substring matching; glob patterns (* ? [ ]) are supported.

Returns: Stored exception records or a summary

browser-heap

Capture heap information for an attached browser session, optionally forcing garbage collection first.

ParameterTypeDescription
collectGarbage

Optional

booleanForce garbage collection before taking the snapshot

Default: false

Returns: Heap snapshot with memory statistics

browser-trace

Control Chrome performance trace recording — start or stop, and configure which trace categories are captured.

ParameterTypeDescription
action

Required

'start' | 'stop'Action: start or stop performance trace recording
categories

Optional

string[]Chrome trace categories to record (e.g., 'devtools.timeline', 'v8.execute'). Defaults to timeline + JS execution.

Returns: Trace recording confirmation or trace data

Emulation
6

Emulate devices, geolocation, vision deficiencies, and network/CPU throttling.

browser-emulate

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

ParameterTypeDescription
userAgent

Optional

stringOverride User-Agent string
colorScheme

Optional

stringEmulate color scheme: light, dark, or no-preference
locale

Optional

stringEmulate locale (e.g., 'en-US')
geolocation

Optional

objectEmulate geolocation: { latitude, longitude, accuracy }
timezoneId

Optional

stringEmulate timezone (e.g., 'America/New_York')
media

Optional

stringEmulate media type: screen or print
offline

Optional

booleanEmulate offline network

Default: false

Returns: Confirmation of emulation settings

browser-resize

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

ParameterTypeDescription
width

Required

numberViewport width in pixels
height

Required

numberViewport height in pixels

Returns: Confirmation

browser-vision

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

ParameterTypeDescription
type

Required

stringVision type: none, blurredVision, reducedContrast, achromatopsia, deuteranopia, protanopia, tritanopia

Returns: Confirmation

browser-cpu

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

ParameterTypeDescription
rate

Required

numberCPU slowdown multiplier (1 = no throttle, 4 = 4× slower)

Returns: Confirmation

browser-throttle

Throttle network speed to simulate different connection conditions.

ParameterTypeDescription
downloadThroughput

Optional

numberDownload speed in bytes/second
uploadThroughput

Optional

numberUpload speed in bytes/second
latency

Optional

numberNetwork latency in milliseconds
offline

Optional

booleanSimulate offline mode

Default: false

Returns: Confirmation

browser-pinch

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

ParameterTypeDescription
gesture

Required

'pinch' | 'scroll' | 'tap'Gesture type: pinch, scroll, or tap
selector

Optional

stringCSS selector or @ref of the target element

Returns: Confirmation

Automation
3

High-level multi-page workflows and batch operations.

browser-crawl

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

ParameterTypeDescription
urls

Required

string[]Starting URLs to crawl
enqueueStrategy

Optional

stringLink discovery strategy: same-hostname, same-domain, same-origin, all
maxRequestsPerCrawl

Optional

numberMaximum total pages to crawl

Default: 100

blockedResources

Optional

string[]Resource types to block: image, stylesheet, font, media
expression

Optional

stringJavaScript expression evaluated in each page context
filePath

Optional

stringFile path to write per-page output to disk

Returns: Per-URL snapshots or expression results

browser-task

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

ParameterTypeDescription
task

Required

stringNatural language task description

Returns: Task execution result with steps taken

browser-animation

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

ParameterTypeDescription
selector

Required

stringCSS selector or @ref of the element to animate
keyframes

Required

object[]CSS keyframes array (e.g., [{ opacity: 0 }, { opacity: 1 }])
options

Optional

objectAnimation timing options (duration, easing, fill, etc.)

Returns: Confirmation

Styling
1

Inspect and manipulate CSS computed styles.

browser-styles

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

ParameterTypeDescription
selector

Required

stringCSS selector or @ref of the target element
properties

Optional

string[]Specific CSS properties to retrieve (e.g., ['color', 'font-size']). Omit for all.

Returns: Record of property names to computed values

AuthenticationRead page snapshots