> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Browser Tool

> Composio 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.

![Browser Tool logo](https://mintcdn.com/composio-preview/PudKL42NVsy5O-ND/images/toolkits/browser_tool.svg?fit=max\&auto=format\&n=PudKL42NVsy5O-ND\&q=85\&s=2230ab7d1d9b0fad945bae59567bcf76)

* **Category:** ai agents
* **Auth:** NO\_AUTH
* **Composio-managed OAuth available?** N/A
* **Tools:** 5
* **Triggers:** 0
* **Slug:** `BROWSER_TOOL`
* **Version:** 20261101\_00

## Tools

> [accordion] Run Browser Task
>
> **Slug:** `BROWSER_TOOL_CREATE_TASK`
>
> Run an AI-powered browser automation task in a new or existing cloud browser session. The agent can navigate websites, fill forms, extract data and handle multi-step workflows; each task is limited to 25 steps.
>
> #### Input Parameters
>
> **task** `string` *required*
>
> Natural language instructions for the browser AI agent. Be specific and clear. Examples: 'Go to amazon.com, search for wireless headphones, and return the top 3 results with prices', 'Log into twitter.com and post a tweet saying Hello World'. For multi-step workflows, break them into clear sequential instructions.
>
> **secrets** `object`
>
> Domain-specific credentials for automatic login. Map domain patterns to 'username:password'. Example: \{'[https://example.com](https://example.com)': '[user@email.com](mailto:user@email.com):pass123', 'https\://*.google.com': '[email@gmail.com](mailto:email@gmail.com):password'}. Wildcards (*) supported for subdomains.
>
> **startUrl** `string`
>
> URL to navigate to before starting the task. If not provided, agent starts from blank page.
>
> **sessionId** `string`
>
> Leave this empty for the first task, a new session will be auto-created. To continue in an existing browser: pass the browser\_session\_id from a previous CreateTask response. This preserves login state and cookies between tasks. Important: the previous task in this session must be finished or stopped (via StopTask or by waiting for WatchTask to show status='finished') before creating a new task.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Download Task File
>
> **Slug:** `BROWSER_TOOL_GET_OUTPUT_FILE`
>
> Get a download URL for a file generated by a task. When a task downloads or creates files (PDFs, images, spreadsheets, etc.), they appear in WatchTask's outputFiles list. Use this to get a download URL. The download URL is temporary (presigned) - download promptly.
>
> #### Input Parameters
>
> **fileId** `string` *required*
>
> File ID from WatchTask's outputFiles list
>
> **taskId** `string` *required*
>
> Task ID from CreateTask
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Session Live URL
>
> **Slug:** `BROWSER_TOOL_GET_SESSION`
>
> Get session status and, when available, a live URL for watching a browser session. Access is restricted to sessions associated with the current user profile.
>
> #### Input Parameters
>
> **sessionId** `string` *required*
>
> The sessionId returned from a CreateTask call you made previously. Only use session IDs from your own CreateTask responses.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Stop Browser Task
>
> **Slug:** `BROWSER_TOOL_STOP_TASK`
>
> Kill a browser task and its session. Use this when the browser agent is in a bad state: - Task is stuck or taking too long - WatchTask shows the agent going in the wrong direction - Agent is looping or making no progress After stopping, call CreateTask again to start fresh with a new browser.
>
> #### Input Parameters
>
> **taskId** `string` *required*
>
> Task ID to stop (from CreateTask)
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Watch Browser Task
>
> **Slug:** `BROWSER_TOOL_WATCH_TASK`
>
> Poll a browser task for progress and results, returning on a terminal status or after up to 30 seconds of polling. Results include status, output, current goal and URL, generated files, and incremental steps with screenshot URLs when available.
>
> #### Input Parameters
>
> **taskId** `string` *required*
>
> The taskId from CreateTask response
>
> **lastStepSeen** `integer`
>
> Last step number from a previous WatchTask response (current\_step value). Only steps after this will be returned for incremental updates. Omit or pass 0 to get all steps.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
