Browserless

Overview

Browserless is a headless browser automation service that provides managed infrastructure for running Puppeteer scripts and performing web automation tasks without the need to manage your own browser server. With the Browserless integration in SquadOS, your agents can download files, execute custom scripts, fetch page HTML, generate PDFs, extract content via CSS selectors, take screenshots, and bypass bot protection reliably.

• Official website: https://www.browserless.io/
• Composio documentation: docs.composio.dev/toolkits/browserless

Authentication

This tool uses API key (API_KEY) to connect.

You will need the following fields:

Field	Required	Description
api_key	Yes	API key from your Browserless account, used to authenticate all requests to the service.

How to get credentials

1. Go to browserless.io and create an account.
2. After signing up, log in to the dashboard at cloud.browserless.io/account.
3. Copy the API Key displayed on your account page — this is the value to enter in the api_key field when connecting in SquadOS.

Tip

Keep your API key confidential. It authenticates all requests and is directly tied to your plan and usage quota.

How to connect in SquadOS

1. Go to Tools in the side menu (/admin/tools).
2. Open the Available tab and search for Browserless.
3. Click the card to open the details modal and hit Connect.
4. You’re taken to the secure connection page hosted by Composio, where you enter the credentials obtained above.
5. Once done, you’re sent back to SquadOS with the account connected and the tool available for your agents. (Connection-flow details in Organization Tools.)

Available actions

Download file using Puppeteer script

BROWSERLESS_DOWNLOAD_FILE

This tool allows downloading files that Chrome has downloaded during the execution of puppeteer code. It sets up a blank page, creates a fresh download directory, injects the provided code, and executes it. Once the script finishes, any downloaded files from Chromium are returned with the appropriate content-type header.

Input parameters

Name	Type	Required	Description
code	string	Yes	The Puppeteer script to execute for downloading the file. This should be a valid JavaScript code that triggers a file download.
context	object	No	Additional context data to be passed to the script.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Execute Custom Function

BROWSERLESS_EXECUTE_CUSTOM_FUNCTION

A tool that allows executing custom Puppeteer scripts via HTTP requests. This endpoint enables users to run browser automation tasks without managing their own infrastructure.

Input parameters

Name	Type	Required	Description
code	string	Yes	The Puppeteer function code to execute. Must be a valid ESM module with a default export function.
context	object	No	Optional context object to pass to the function. Supports any JSON-serializable nested data.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Fetch HTML Content

BROWSERLESS_FETCH_HTML_CONTENT

This tool fetches the complete HTML content of a webpage using Browserless’s content API. It’s designed to retrieve the full HTML contents of any website, including dynamically generated content.

Input parameters

Name	Type	Required	Description
url	string	Yes	The URL of the webpage to fetch HTML content from.
best_attempt	boolean	No	Whether to continue on error.
goto_options	object	No	Navigation options like waitUntil.
wait_for_event	object	No	Wait for specific event with optional timeout.
wait_for_timeout	integer	No	Wait for specific time in milliseconds.
wait_for_selector	object	No	Wait for specific element with optional timeout.
reject_resource_types	array	No	Types of resources to block (e.g., images, stylesheets).
reject_request_pattern	array	No	Patterns to block specific requests.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Generate PDF from webpage

BROWSERLESS_GENERATE_PDF

This tool generates a PDF from a specified webpage using Browserless’s PDF generation API. It allows specifying the URL of the webpage along with parameters such as format, filename, and waitUntil options to control the PDF generation process.

Input parameters

Name	Type	Required	Description
url	string	No	URL of the webpage to generate PDF from.
html	string	No	HTML content to generate PDF from.
options	object	No	PDF generation options based on Puppeteer’s PDFOptions.
addStyleTag	array	No	Custom style tags to inject.
bestAttempt	boolean	No	Continue on error.
gotoOptions	object	No	Navigation options for page loading.
addScriptTag	array	No	Custom script tags to inject.
waitForSelector	object	No	Options for waiting for a selector to appear.
rejectResourceTypes	array	No	Resource types to block.
rejectRequestPattern	array	No	Request patterns to block.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Scrape webpage content using CSS selectors

BROWSERLESS_SCRAPE_CONTENT

A tool to extract structured content from a webpage by specifying CSS selectors. The tool navigates to the specified URL, waits for the page to load (including parsing and executing JavaScript), and returns the selected elements in a structured JSON format.

Input parameters

Name	Type	Required	Description
url	string	Yes	The URL to scrape content from.
elements	array	Yes	Array of objects containing CSS selectors to extract.
gotoOptions	object	No	Options for page navigation.
waitForEvent	object	No	Wait for a specific event to occur.
waitForTimeout	integer	No	Wait specified milliseconds before scraping.
waitForFunction	object	No	Wait for a custom JavaScript function to return true.
waitForSelector	object	No	Wait for a specific selector to appear.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Take Screenshot

BROWSERLESS_TAKE_SCREENSHOT

A tool that captures a screenshot of a webpage using Browserless’s screenshot API. The tool takes a URL and returns either a PNG or JPEG image. It includes options for full page capture, image type, quality, and clipping coordinates.

Input parameters

Name	Type	Required	Description
url	string	Yes	The URL of the webpage to capture.
clip_x	integer	No	X coordinate for clipping the screenshot.
clip_y	integer	No	Y coordinate for clipping the screenshot.
quality	integer	No	The quality of the image (0–100, only applies to jpeg).
full_page	boolean	No	Whether to capture the full page or just the viewport.
clip_width	integer	No	Width of the clipping area.
image_type	string	No	The type of image to return (png or jpeg).
clip_height	integer	No	Height of the clipping area.
omit_background	boolean	No	Whether to omit the background in the screenshot.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.

Unblock Protected Content

BROWSERLESS_UNBLOCK_PROTECTED_CONTENT

This tool provides access to content from websites that implement bot protection mechanisms. It is designed to bypass various types of protection (such as CAPTCHA and bot detections) and return the HTML content of the protected webpage, with optional customization through parameters like waitFor, timeout, and stealth mode.

Input parameters

Name	Type	Required	Description
ttl	integer	No	Time to live for the browser instance in milliseconds.
url	string	Yes	The URL of the protected webpage to access.
content	boolean	No	Whether to return the HTML content of the page.
cookies	boolean	No	Whether to return cookies from the page.
screenshot	boolean	No	Whether to return a screenshot of the page.
waitForEvent	object	No	Event to wait for before returning the response.
waitForFunction	object	No	Function to execute and wait for before returning the response.
waitForSelector	object	No	Selector to wait for before returning the response.
browserWSEndpoint	boolean	No	Whether to return a WebSocket endpoint for browser automation.

Output

Name	Type	Required	Description
data	string	Yes	Data from the action execution.
error	string	No	Error if any occurred during the execution of the action.
successful	boolean	Yes	Whether or not the action execution was successful.