Hyperbrowser

Learn how to use Hyperbrowser with Composio

Overview

SLUG: HYPERBROWSER

Description

Hyperbrowser is a next-generation platform empowering AI agents and enabling effortless, scalable browser automation.

Authentication Details

generic_api_key
stringRequired

Connecting to Hyperbrowser

Create an auth config

Use the dashboard to create an auth config for the Hyperbrowser toolkit. This allows you to connect multiple Hyperbrowser accounts to Composio for agents to use.

1

Select App

Navigate to Hyperbrowser.

2

Configure Auth Config Settings

Select among the supported auth schemes of and configure them here.

3

Create and Get auth config ID

Click “Create Hyperbrowser Auth Config”. After creation, copy the displayed ID starting with ac_. This is your auth config ID. This is not a sensitive ID — you can save it in environment variables or a database. This ID will be used to create connections to the toolkit for a given user.

Connect Your Account

Using API Key

1from composio import Composio
2
3# Replace these with your actual values
4hyperbrowser_auth_config_id = "ac_YOUR_HYPERBROWSER_CONFIG_ID" # Auth config ID created above
5user_id = "0000-0000-0000" # UUID from database/app
6
7composio = Composio()
8
9def authenticate_toolkit(user_id: str, auth_config_id: str):
10 # Replace this with a method to retrieve an API key from the user.
11 # Or supply your own.
12 user_api_key = input("[!] Enter API key")
13
14 connection_request = composio.connected_accounts.initiate(
15 user_id=user_id,
16 auth_config_id=auth_config_id,
17 config={"auth_scheme": "API_KEY", "val": {"generic_api_key": user_api_key}}
18 )
19
20 # API Key authentication is immediate - no redirect needed
21 print(f"Successfully connected Hyperbrowser for user {user_id}")
22 print(f"Connection status: {connection_request.status}")
23
24 return connection_request.id
25
26
27connection_id = authenticate_toolkit(user_id, hyperbrowser_auth_config_id)
28
29# You can verify the connection using:
30connected_account = composio.connected_accounts.get(connection_id)
31print(f"Connected account: {connected_account}")

Tools

Executing tools

To prototype you can execute some tools to see the responses and working on the Hyperbrowser toolkit’s playground

Python
1from composio import Composio
2from openai import OpenAI
3import json
4
5openai = OpenAI()
6composio = Composio()
7
8# User ID must be a valid UUID format
9user_id = "0000-0000-0000" # Replace with actual user UUID from your database
10
11tools = composio.tools.get(user_id=user_id, toolkits=["HYPERBROWSER"])
12
13print("[!] Tools:")
14print(json.dumps(tools))
15
16def invoke_llm(task = "What can you do?"):
17 completion = openai.chat.completions.create(
18 model="gpt-4o",
19 messages=[
20 {
21 "role": "user",
22 "content": task, # Your task here!
23 },
24 ],
25 tools=tools,
26 )
27
28 # Handle Result from tool call
29 result = composio.provider.handle_tool_calls(user_id=user_id, response=completion)
30 print(f"[!] Completion: {completion}")
31 print(f"[!] Tool call result: {result}")
32
33invoke_llm()

Tool List

Tool Name: Create Hyperbrowser Profile

Description

Tool to create a new profile. Use when you need to initialize a Hyperbrowser profile before analysis.

Action Parameters

name
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Create Scrape Job

Description

Tool to initiate a new scrape job. Use when you need to extract structured content from a target URL with custom session and scrape settings.

Action Parameters

scrapeOptions
object
sessionOptions
object
url
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Create Session

Description

Tool to create a new browser session with custom stealth, proxy, and privacy settings. Use when initializing an automated browsing session with specific configuration.

Action Parameters

acceptCookies
boolean
adblock
boolean
annoyances
boolean
browserArgs
array
device
array
enableVideoWebRecording
boolean
enableWebRecording
booleanDefaults to True
extensionIds
array
imageCaptchaParams
array
locales
array
operatingSystems
array
platform
array
profile
object
proxyCity
string
proxyCountry
string
proxyServer
string
proxyServerPassword
string
proxyServerUsername
string
proxyState
string
screen
object
solveCaptchas
boolean
timeoutMinutes
integer
trackers
boolean
urlBlocklist
array
useProxy
boolean
useStealth
boolean

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Delete Profile

Description

Tool to delete a profile. Use when you need to remove a profile by its unique identifier after confirming its existence.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get browser-use task status

Description

Tool to retrieve the current status of a browser-use task. Use when checking if a browser automation task has completed or is still pending.

Action Parameters

task_id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Claude Computer Use Task Status

Description

Tool to retrieve the status of a Claude Computer Use task. Use after creating a task to poll its status.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Crawl Job Result

Description

Tool to retrieve the result of a completed crawl job. Use after confirming crawl job completion to fetch current page batch and status. Supports pagination via page and batchSize.

Action Parameters

batchSize
integer
id
stringRequired
page
integer

Action Response

batchSize
integerRequired
currentPageBatch
integerRequired
data
arrayRequired
error
string
jobId
stringRequired
status
stringRequired
successful
booleanRequired
totalCrawledPages
integerRequired
totalPageBatches
integerRequired

Tool Name: Get Crawl Job Status

Description

Tool to retrieve the status and results of a specific crawl job. Use after submitting a crawl job to check its progress or fetch results.

Action Parameters

job_id
stringRequired

Action Response

batchSize
integerRequired
currentPageBatch
integerRequired
data
arrayRequired
error
string
jobId
stringRequired
status
stringRequired
successful
booleanRequired
totalCrawledPages
integerRequired
totalPageBatches
integerRequired

Tool Name: Get Extract Job Result

Description

Tool to fetch the status and results of a specific extract job. Use after initiating an extract job to monitor progress and retrieve final data.

Action Parameters

id
stringRequired

Action Response

data
error
string
jobId
stringRequired
status
stringRequired
successful
booleanRequired

Tool Name: Get Extract Job Status

Description

Tool to retrieve the status of an extract job. Use after submitting an extract job to poll its status.

Action Parameters

job_id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Profile By ID

Description

Tool to retrieve profile details by ID. Use after confirming the profile ID.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Scrape Job Result

Description

Tool to fetch the status and results of a specific scrape job. Use after initiating a scrape job to monitor its progress and retrieve final data.

Action Parameters

id
stringRequired

Action Response

data
object
error
string
jobId
stringRequired
status
stringRequired
successful
booleanRequired

Tool Name: Get Scrape Job Status

Description

Tool to retrieve the current status of a specific scrape job. Use after initiating a scrape job to poll its status.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Session Details

Description

Tool to retrieve session details by ID. Use after confirming the session ID.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Session Downloads URL

Description

Tool to retrieve the downloads URL for a session. Use when you need the signed URL for session downloads after processing is complete.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Get Session Recording

Description

Tool to retrieve the recording URL of a session. Use after confirming the session ID and when the recording is expected to be ready.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Profiles

Description

Tool to list profiles. Use when you need to fetch paginated profiles and optionally filter by name.

Action Parameters

limit
integerDefaults to 10
name
string
page
integerDefaults to 1

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Sessions

Description

Tool to list sessions with optional status filter. Use when you need a paginated overview of browser sessions before acting on them.

Action Parameters

page
integerDefaults to 1
status
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Start Browser Use Task

Description

Tool to start an asynchronous browser-use task. Use when you need to automate web interactions given a task instruction.

Action Parameters

apiKeys
object
initialActions
array
keepBrowserOpen
boolean
llm
stringDefaults to gemini-2.0-flash
maxActionsPerStep
integerDefaults to 10
maxFailures
integerDefaults to 3
maxInputTokens
integerDefaults to 128000
maxSteps
integerDefaults to 20
pageExtractionLlm
stringDefaults to gemini-2.0-flash
plannerInterval
integerDefaults to 10
plannerLlm
stringDefaults to gemini-2.0-flash
sessionId
string
sessionOptions
object
task
stringRequired
useCustomApiKeys
boolean
useVision
booleanDefaults to True
useVisionForPlanner
boolean
validateOutput
boolean

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Start Claude Computer Use Task

Description

Tool to start a Claude Computer Use task. Use when you need AI-driven automated browser interactions. Call after you have your task prompt and any session preferences configured.

Action Parameters

apiKeys
object
keepBrowserOpen
boolean
llm
stringDefaults to claude-3-7-sonnet-20250219
maxFailures
integerDefaults to 3
maxSteps
integerDefaults to 20
sessionId
string
sessionOptions
object
task
stringRequired
useComputerAction
boolean
useCustomApiKeys
boolean

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Start Crawl Job

Description

Tool to start a new crawl job for a specified URL. Use when you need to initiate a web crawl before checking job status.

Action Parameters

excludePatterns
array
followLinks
booleanDefaults to True
ignoreSitemap
boolean
includePatterns
array
maxPages
integer
scrapeOptions
object
sessionOptions
object
url
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Start Extract Job

Description

Tool to start an extract job. Use when you need to initiate a new extraction with custom prompts, schema, and session options. Call after preparing URLs and desired extraction schema.

Action Parameters

maxLinks
integer
prompt
string
schema
object
sessionOptions
object
systemPrompt
string
urls
arrayRequired
waitFor
integer

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Stop Browser Use Task

Description

Tool to stop a running browser-use task. Use when halting an in-progress browser automation task after confirming its task ID.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Stop Claude Computer Use Task

Description

Tool to stop a running Claude computer use task. Use when a Claude computer use task is in progress and needs to be terminated.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Stop Session

Description

Tool to stop a running session by ID. Use after confirming the session is active.

Action Parameters

id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired