Browser Tool
browser_toolComposio Browser Tool enables AI Agents and LLMs to automate web interactions, perform web scraping, and conduct automated testing. Use cases include data extraction, form automation, website monitoring, and intelligent web navigation.
Acciones disponibles (18)
Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.
Copy Selected TextBROWSER_TOOL_COPY_SELECTED_TEXTAcciónCopy currently selected text on the page to clipboard - ideal for extracting highlighted content, copying form data, or harvesting visible text selections.
BROWSER_TOOL_COPY_SELECTED_TEXTAcciónCopy currently selected text on the page to clipboard - ideal for extracting highlighted content, copying form data, or harvesting visible text selections.
Parámetros de entrada
Sin parámetros.
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Drag and DropBROWSER_TOOL_DRAG_AND_DROPAcciónExecute precise drag and drop operations - essential for file uploads, list reordering, element moving, and complex ui interactions that require drag-based manipulation.
BROWSER_TOOL_DRAG_AND_DROPAcciónExecute precise drag and drop operations - essential for file uploads, list reordering, element moving, and complex ui interactions that require drag-based manipulation.
Parámetros de entrada
endXintegerObligatorioEnding X coordinate for drop operation (where to release the element)
endYintegerObligatorioEnding Y coordinate for drop operation (where to release the element)
buttonstringMouse button for drag operation (almost always 'left' for standard drag-drop, 'right' for special contexts)
startXintegerObligatorioStarting X coordinate for drag operation (where to grab the element)
startYintegerObligatorioStarting Y coordinate for drag operation (where to grab the element)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Fetch Webpage ContentBROWSER_TOOL_FETCH_WEBPAGEAcciónYour eyes: get page content for decision-making. use before: actions (find targets, understand state) use to verify: page transitions, major state changes, when actions seem to fail format: html=find elements | markdown=clean content | success rate: 99%
BROWSER_TOOL_FETCH_WEBPAGEAcciónYour eyes: get page content for decision-making. use before: actions (find targets, understand state) use to verify: page transitions, major state changes, when actions seem to fail format: html=find elements | markdown=clean content | success rate: 99%
Parámetros de entrada
urlstringURL to fetch content from. If not provided, uses current page
waitintegerTime to wait for dynamic content to load (milliseconds)
formatstringOutput format for content (markdown or html)
newPagebooleanWhether to create a new page for the content
idleTtlSecintegerOptional idle TTL for new sessions (seconds)
returnPartialOnTimeoutbooleanWhether to return partial content if timeout occurs
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Get Clipboard ContentBROWSER_TOOL_GET_CLIPBOARDAcciónRead current content from the system clipboard - essential for data transfer workflows, extracting copied text, and reading user-copied data for processing.
BROWSER_TOOL_GET_CLIPBOARDAcciónRead current content from the system clipboard - essential for data transfer workflows, extracting copied text, and reading user-copied data for processing.
Parámetros de entrada
Sin parámetros.
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Keyboard ShortcutBROWSER_TOOL_KEYBOARD_SHORTCUTAcciónExecute keyboard shortcuts and key combinations - essential for copy/paste, navigation, and application commands that agents need for efficient browser automation.
BROWSER_TOOL_KEYBOARD_SHORTCUTAcciónExecute keyboard shortcuts and key combinations - essential for copy/paste, navigation, and application commands that agents need for efficient browser automation.
Parámetros de entrada
keysstring[]ObligatorioArray of keys to press simultaneously (e.g., ['Ctrl', 'c'] for copy, ['Alt', 'Tab'] for window switching, ['Ctrl', 'Shift', 'I'] for dev tools)
holdTimeintegerMilliseconds to hold keys down (0=quick press like normal shortcuts, 100+=sustained press for special actions)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Mouse ClickBROWSER_TOOL_MOUSE_CLICKAcciónPrecision clicker: manual clicking with coordinates. pattern: fetchwebpage(html) → find element → estimate coordinates → click → verify hints: center buttons ~(640,350) | nav/header ~y=150 | content ~y=300-500 tip: try ±50px if first click misses | success rate: 85%
BROWSER_TOOL_MOUSE_CLICKAcciónPrecision clicker: manual clicking with coordinates. pattern: fetchwebpage(html) → find element → estimate coordinates → click → verify hints: center buttons ~(640,350) | nav/header ~y=150 | content ~y=300-500 tip: try ±50px if first click misses | success rate: 85%
Parámetros de entrada
xintegerObligatorioX coordinate to click
yintegerObligatorioY coordinate to click
buttonstringMouse button to use for clicking
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Mouse Double ClickBROWSER_TOOL_MOUSE_DOUBLE_CLICKAcciónExecute a precise double click at specified screen coordinates - ideal for opening files, selecting text, or activating ui elements that require double click gestures.
BROWSER_TOOL_MOUSE_DOUBLE_CLICKAcciónExecute a precise double click at specified screen coordinates - ideal for opening files, selecting text, or activating ui elements that require double click gestures.
Parámetros de entrada
xintegerObligatorioHorizontal pixel position for double click (0 = left edge, increases rightward)
yintegerObligatorioVertical pixel position for double click (0 = top edge, increases downward)
buttonstringMouse button for double click action - use 'left' for most UI elements, 'right' for context menus
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Mouse Down (Press and Hold)BROWSER_TOOL_MOUSE_DOWNAcciónPress and hold mouse button at coordinates - use for starting custom drag operations, text selections, or long-press interactions. must be followed by mouseup action to complete.
BROWSER_TOOL_MOUSE_DOWNAcciónPress and hold mouse button at coordinates - use for starting custom drag operations, text selections, or long-press interactions. must be followed by mouseup action to complete.
Parámetros de entrada
xintegerObligatorioX coordinate to press mouse button down (where to start the press-and-hold operation)
yintegerObligatorioY coordinate to press mouse button down (where to start the press-and-hold operation)
buttonstringMouse button to press and hold (usually 'left' for selections and drags, 'right' for context menus)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Mouse MoveBROWSER_TOOL_MOUSE_MOVEAcciónMove mouse cursor to precise coordinates without clicking - perfect for triggering hover effects, revealing tooltips, and positioning for subsequent interactions.
BROWSER_TOOL_MOUSE_MOVEAcciónMove mouse cursor to precise coordinates without clicking - perfect for triggering hover effects, revealing tooltips, and positioning for subsequent interactions.
Parámetros de entrada
xintegerObligatorioTarget X coordinate for mouse cursor (0 = left edge, increases rightward, typical screen: 0-1440px)
yintegerObligatorioTarget Y coordinate for mouse cursor (0 = top edge, increases downward, typical screen: 0-900px)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Mouse Up (Release Button)BROWSER_TOOL_MOUSE_UPAcciónRelease mouse button at coordinates - completes drag operations, text selections, and long-press interactions. should be used after mousedown to finish mouse button sequences.
BROWSER_TOOL_MOUSE_UPAcciónRelease mouse button at coordinates - completes drag operations, text selections, and long-press interactions. should be used after mousedown to finish mouse button sequences.
Parámetros de entrada
xintegerObligatorioX coordinate to release mouse button (where to end the press-and-hold operation or complete a drag)
yintegerObligatorioY coordinate to release mouse button (where to end the press-and-hold operation or complete a drag)
buttonstringMouse button to release (should match the button used in previous MouseDown action)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Navigate to URLBROWSER_TOOL_NAVIGATEAcciónAlways start here: creates browser session and navigates to url. workflow: navigate() → fetchwebpage() → manual interactions → verify print debugurl to user | success rate: 99%
BROWSER_TOOL_NAVIGATEAcciónAlways start here: creates browser session and navigates to url. workflow: navigate() → fetchwebpage() → manual interactions → verify print debugurl to user | success rate: 99%
Parámetros de entrada
urlstringObligatorioURL to navigate the cloud browser to
idleTtlSecintegerOptional idle TTL for the session (seconds)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Paste TextBROWSER_TOOL_PASTE_TEXTAcciónPaste text content at the current cursor position - perfect for filling forms, inserting data into text fields, or quick content insertion at focused elements.
BROWSER_TOOL_PASTE_TEXTAcciónPaste text content at the current cursor position - perfect for filling forms, inserting data into text fields, or quick content insertion at focused elements.
Parámetros de entrada
textstringObligatorioText content to paste at current cursor location (form data, URLs, structured content)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
AI Perform Web TaskBROWSER_TOOL_PERFORM_WEB_TASKAcciónAi automation: complex workflows only. when to use: 10+ manual steps | dynamic/unpredictable content when to avoid: simple clicks | forms | navigation | payments strategy: try once → if fails, switch to manual immediately success rate: 40% - always have manual backup ready
BROWSER_TOOL_PERFORM_WEB_TASKAcciónAi automation: complex workflows only. when to use: 10+ manual steps | dynamic/unpredictable content when to avoid: simple clicks | forms | navigation | payments strategy: try once → if fails, switch to manual immediately success rate: 40% - always have manual backup ready
Parámetros de entrada
urlstringOptional URL to perform task on (if not provided, uses current page in existing session)
promptstringObligatorioNatural language description of the web task to perform autonomously (e.g., 'Log into Gmail and send an email', 'Fill out contact form', 'Find and download the PDF')
aiAgentstringAI agent engine to use ('browser-use'=robust multi-step automation, 'openai-cua'=OpenAI-optimized tasks)
aiModelstringSpecific AI model to use ('gpt-5'=latest flagship, 'gpt-5-mini'=efficient flagship, 'gpt-5-nano'=ultra-fast, 'gpt-4o'=advanced OpenAI, 'gpt-4o-mini'=efficient, 'gpt-4.1'=enhanced, 'gpt-4.1-mini'=compact enhanced)
aiProviderstringAI provider for task execution ('openai'=GPT models, 'gemini'=Google AI, 'groq'=fast inference, 'azure'=enterprise, 'xai'=experimental)
idleTtlSecintegerOptional idle TTL for new sessions if sessionId not provided (seconds)
outputSchemaobjectOptional JSON Schema to structure the output for data extraction tasks (provides structured data instead of text description)
highlightElementsbooleanShow visual highlights during task execution for transparency and debugging (True=show interaction highlights, False=hidden execution)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Screenshot WebpageBROWSER_TOOL_SCREENSHOT_WEBPAGEAcciónCapture high-quality screenshot of any webpage with extensive customization options - perfect for archiving, visual documentation, full-page captures, and cross-device viewport testing.
BROWSER_TOOL_SCREENSHOT_WEBPAGEAcciónCapture high-quality screenshot of any webpage with extensive customization options - perfect for archiving, visual documentation, full-page captures, and cross-device viewport testing.
Parámetros de entrada
urlstringObligatorioURL of the webpage to capture (can be any publicly accessible website)
waitintegerMilliseconds to wait after page load for JS/animations (1000=default, 3000+=heavy sites, 5000+=very dynamic)
widthintegerBrowser viewport width in pixels for capture (1280=standard desktop, 1440=large desktop, 375=mobile)
heightintegerBrowser viewport height in pixels for capture (720=standard, 900=tall desktop, 667=mobile)
idleTtlSecintegerOptional idle TTL for new sessions if sessionId not provided (seconds)
imageQualityintegerImage quality percentage (100=no compression/max quality, 80=good balance, 50=smaller file size)
scrollAllContentbooleanScroll through entire page to capture all content (True=captures everything, False=viewport only)
captureFullHeightbooleanCapture entire page height ignoring viewport (True=full page length, False=viewport height only)
Parámetros de salida
datastringObligatorioBase64 encoded image data
errorstringError if any occurred during the execution of the action
mimeTypestringObligatorioMIME type of the image
successfulbooleanObligatorioWhether or not the action execution was successful or not
Scroll PageBROWSER_TOOL_SCROLLAcciónPage navigation: smooth scrolling. use: when target element not visible after fetchwebpage() distance: 200px=fine | 400px=sections | 800px=quick traverse always: scroll → fetchwebpage() → verify | success rate: 99%
BROWSER_TOOL_SCROLLAcciónPage navigation: smooth scrolling. use: when target element not visible after fetchwebpage() distance: 200px=fine | 400px=sections | 800px=quick traverse always: scroll → fetchwebpage() → verify | success rate: 99%
Parámetros de entrada
xintegerX coordinate where scroll originates (center of viewport recommended: 640 for 1280px width, 720 for 1440px width)
yintegerY coordinate where scroll originates (center of viewport recommended: 360 for 720px height, 400 for 800px height)
stepsintegerNumber of steps to break scroll into for smoothness (1=instant jump, 3-5=smooth animation, 10+=very smooth but slower)
useOsbooleanUse OS-level scrolling (True=more reliable, works with all apps) vs browser scrolling (False=web-specific, may fail on some sites)
deltaXintegerHorizontal scroll distance in pixels (positive=scroll right, negative=scroll left, usually 0 for vertical scrolling)
deltaYintegerObligatorioVertical scroll distance in pixels (positive=scroll down toward bottom, negative=scroll up toward top, typical range: 100-500px per scroll)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Set Clipboard ContentBROWSER_TOOL_SET_CLIPBOARDAcciónStore text content in the system clipboard for later paste operations - perfect for preparing data transfers, staging content for forms, or cross-application data sharing.
BROWSER_TOOL_SET_CLIPBOARDAcciónStore text content in the system clipboard for later paste operations - perfect for preparing data transfers, staging content for forms, or cross-application data sharing.
Parámetros de entrada
textstringObligatorioText content to store in system clipboard (URLs, data, structured text, form content)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Take ScreenshotBROWSER_TOOL_TAKE_SCREENSHOTAcciónVisual verification: capture screenshot of current browser viewport. use: debug ui issues, verify page state, document visual results renders: inline in mcp clients for immediate visual feedback tip: use after page changes to confirm they worked | success rate: 99%
BROWSER_TOOL_TAKE_SCREENSHOTAcciónVisual verification: capture screenshot of current browser viewport. use: debug ui issues, verify page state, document visual results renders: inline in mcp clients for immediate visual feedback tip: use after page changes to confirm they worked | success rate: 99%
Parámetros de entrada
Sin parámetros.
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not
Type TextBROWSER_TOOL_TYPE_TEXTAcciónControlled input: human-like typing. pattern: click to focus → typetext() → verify speed: delay=0 (fast) | delay=50 (human-like) | delay=100+ (careful) must focus input field first | success rate: 95%
BROWSER_TOOL_TYPE_TEXTAcciónControlled input: human-like typing. pattern: click to focus → typetext() → verify speed: delay=0 (fast) | delay=50 (human-like) | delay=100+ (careful) must focus input field first | success rate: 95%
Parámetros de entrada
textstringObligatorioText content to type into the browser (supports unicode, special characters, newlines, form data)
delayintegerMilliseconds delay between each keystroke for natural human-like typing (0=instant, 50-100=realistic human speed, 200+=slow deliberate typing)
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not