The Hyperbrowser connector lets your AI agent act in each user's Hyperbrowser account. Each user connects their own Hyperbrowser API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 60 tools.
- Tools
- 60
- What they doRead · write · destructive
- 35 · 16 · 935 read16 write9 destructive
- Users sign in with
- API key
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the Hyperbrowser connection
In AgentKit > Connections, create a Hyperbrowser connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'hyperbrowser'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize Hyperbrowser:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'hyperbrowser_extensions_list',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "hyperbrowser"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize Hyperbrowser:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="hyperbrowser_extensions_list",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user opens the link once and enters their Hyperbrowser credentials there. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_toolhyperbrowser_browser_use_task_getGet a Browser Use task's status, steps and final result.Read-onlyGet Browser Use Task
Get a Browser Use task's status, steps and final result. Returns the task object. Poll until the status is completed or failed.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_browser_use_task_status_getGet only the status of a Browser Use task.Read-onlyGet Browser Use Task Status
Get only the status of a Browser Use task. Returns the status. Use hyperbrowser_browser_use_task_get for the result.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_claude_computer_use_task_getGet a Claude Computer Use task's status, steps and final result.Read-onlyGet Claude Computer Use Task
Get a Claude Computer Use task's status, steps and final result. Returns the task object. Poll until the status is completed or failed.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_claude_computer_use_task_status_getGet only the status of a Claude Computer Use task.Read-onlyGet Claude Computer Use Task Status
Get only the status of a Claude Computer Use task. Returns the status. Use hyperbrowser_claude_computer_use_task_get for the result.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_crawl_getGet a crawl job's status and crawled pages, a page of results at a time.Read-onlyGet Crawl Job
Get a crawl job's status and crawled pages, a page of results at a time. Returns the job with page results. Poll until the status is completed or failed.
Inputs
crawl_job_idstringrequired- ID of the crawl job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
batch_sizeinteger- Number of page results per response page. Example: 20.
pageinteger- Page number of results, starting at 1. Example: 1.
hyperbrowser_crawl_status_getGet only the status of a crawl job.Read-onlyGet Crawl Job Status
Get only the status of a crawl job. Returns the status. Use hyperbrowser_crawl_get for the pages.
Inputs
crawl_job_idstringrequired- ID of the crawl job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_extensions_listList the Chrome extensions uploaded to the account.Read-onlyList Extensions
List the Chrome extensions uploaded to the account. Returns extension IDs and names. Pass IDs as extension_ids to hyperbrowser_session_create; extensions are uploaded in the dashboard.
Inputs
This tool takes no inputs.
hyperbrowser_extract_getGet an extract job's status and, once completed, the extracted data.Read-onlyGet Extract Job
Get an extract job's status and, once completed, the extracted data. Returns the job object. Poll until the status is completed or failed.
Inputs
extract_job_idstringrequired- ID of the extract job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_extract_status_getGet only the status of an extract job.Read-onlyGet Extract Job Status
Get only the status of an extract job. Returns the status. Use hyperbrowser_extract_get for the data.
Inputs
extract_job_idstringrequired- ID of the extract job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_gemini_computer_use_task_getGet a Gemini Computer Use task's status, steps and final result.Read-onlyGet Gemini Computer Use Task
Get a Gemini Computer Use task's status, steps and final result. Returns the task object. Poll until the status is completed or failed.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_gemini_computer_use_task_status_getGet only the status of a Gemini Computer Use task.Read-onlyGet Gemini Computer Use Task Status
Get only the status of a Gemini Computer Use task. Returns the status. Use hyperbrowser_gemini_computer_use_task_get for the result.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_hyper_agent_task_getGet a HyperAgent task's status, steps and final result.Read-onlyGet HyperAgent Task
Get a HyperAgent task's status, steps and final result. Returns the task object. Poll until the status is completed or failed.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_hyper_agent_task_status_getGet only the status of a HyperAgent task.Read-onlyGet HyperAgent Task Status
Get only the status of a HyperAgent task. Returns the status. Use hyperbrowser_hyper_agent_task_get for the result.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_openai_cua_task_getGet a OpenAI CUA task's status, steps and final result.Read-onlyGet OpenAI CUA Task
Get a OpenAI CUA task's status, steps and final result. Returns the task object. Poll until the status is completed or failed.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_openai_cua_task_status_getGet only the status of a OpenAI CUA task.Read-onlyGet OpenAI CUA Task Status
Get only the status of a OpenAI CUA task. Returns the status. Use hyperbrowser_openai_cua_task_get for the result.
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_profile_getGet one browser profile by ID.Read-onlyGet Profile
Get one browser profile by ID. Returns the profile with its name and timestamps. Get profile IDs from hyperbrowser_profiles_list.
Inputs
profile_idstringrequired- ID of the profile. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_profiles_listList saved browser profiles, optionally filtered by name, a page at a time.Read-onlyList Profiles
List saved browser profiles, optionally filtered by name, a page at a time. Returns profile IDs and names.
Inputs
limitnumber- Number of results per page. Example: 20.
namestring- Filter by profile name. Example: checkout-login.
pagenumber- Page number of results, starting at 1. Example: 1.
hyperbrowser_sandbox_getGet one sandbox by ID with its status, image, resources and exposed ports.Read-onlyGet Sandbox
Get one sandbox by ID with its status, image, resources and exposed ports. Returns the sandbox object. Get IDs from hyperbrowser_sandboxes_list.
Inputs
sandbox_idstringrequired- ID of the sandbox. Example: sbx_9a8b7c6d.
hyperbrowser_sandboxes_listList sandboxes, optionally filtered by status, creation time or ID search, a page at a time.Read-onlyList Sandboxes
List sandboxes, optionally filtered by status, creation time or ID search, a page at a time. Returns sandbox IDs, statuses and images.
Inputs
endnumber- Only sandboxes created at or before this time, in epoch milliseconds. Example: 1767312000000.
limitinteger- Number of results per page. Example: 20.
pageinteger- Page number of results, starting at 1. Example: 1.
searchstring- Search text. Example: warm.
startnumber- Only sandboxes created at or after this time, in epoch milliseconds. Example: 1767225600000.
statusstring- Filter by status. Example: active.one of
activestoppingclosedclose-errorerror
hyperbrowser_scrape_batch_getGet a batch scrape job's status and the scraped pages, a page of results at a time.Read-onlyGet Batch Scrape Job
Get a batch scrape job's status and the scraped pages, a page of results at a time. Returns the job with per-URL results. Poll until the status is completed or failed.
Inputs
batch_scrape_job_idstringrequired- ID of the batch scrape job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_scrape_batch_status_getGet only the status of a batch scrape job.Read-onlyGet Batch Scrape Job Status
Get only the status of a batch scrape job. Returns the status. Use hyperbrowser_scrape_batch_get for the results.
Inputs
batch_scrape_job_idstringrequired- ID of the batch scrape job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_scrape_getGet a scrape job's status and, once completed, the page content in the requested formats.Read-onlyGet Scrape Job
Get a scrape job's status and, once completed, the page content in the requested formats. Returns the job object. Poll until the status is completed or failed.
Inputs
scrape_job_idstringrequired- ID of the scrape job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_scrape_status_getGet only the status of a scrape job (pending, running, completed or failed).Read-onlyGet Scrape Job Status
Get only the status of a scrape job (pending, running, completed or failed). Returns the status. Use hyperbrowser_scrape_get for the content.
Inputs
scrape_job_idstringrequired- ID of the scrape job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_session_downloads_url_getGet a URL to the archive of files downloaded during a session started with save_downloads.Read-onlyGet Session Downloads URL
Get a URL to the archive of files downloaded during a session started with save_downloads. Returns the archive status and a temporary URL.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_session_getGet one browser session by ID with its status, settings, start and end times and connection URLs.Read-onlyGet Browser Session
Get one browser session by ID with its status, settings, start and end times and connection URLs. Returns the session object. Get session IDs from hyperbrowser_sessions_list.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_session_recording_url_getGet the replay (rrweb) recording URL of a session started with web recording enabled.Read-onlyGet Session Recording URL
Get the replay (rrweb) recording URL of a session started with web recording enabled. Returns the recording status and a temporary URL.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_session_video_recording_url_getGet the video recording URL of a session started with video recording enabled.Read-onlyGet Session Video Recording URL
Get the video recording URL of a session started with video recording enabled. Returns the recording status and a temporary URL.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_session_webmcp_tools_listList the WebMCP tools that pages open in a session expose, across tabs and frames.Read-onlyList Session WebMCP Tools
List the WebMCP tools that pages open in a session expose, across tabs and frames. Returns tool references, names, input schemas and their source page. The session must have WebMCP enabled. Call a tool with hyperbrowser_session_webmcp_tool_invoke.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_sessions_listList browser sessions, optionally only active, closed or errored ones, a page at a time.Read-onlyList Browser Sessions
List browser sessions, optionally only active, closed or errored ones, a page at a time. Returns session IDs, statuses and times. Use hyperbrowser_session_get for one session.
Inputs
pagenumber- Page number of results, starting at 1. Example: 1.
statusstring- Filter by status. Example: active.one of
activeclosederrorclose-error
hyperbrowser_volume_getGet one volume by ID.Read-onlyGet Volume
Get one volume by ID. Returns the volume with its name, size and timestamps.
Inputs
volume_idstringrequired- ID of the volume. Example: vol_12ab34.
hyperbrowser_volumes_listList persistent volumes, optionally searched by name or ID, a page at a time.Read-onlyList Volumes
List persistent volumes, optionally searched by name or ID, a page at a time. Returns volume IDs, names and sizes.
Inputs
limitinteger- Number of results per page. Example: 20.
pageinteger- Page number of results, starting at 1. Example: 1.
searchstring- Search text. Example: warm.
hyperbrowser_web_crawl_getGet a web crawl job's status and page results, a page at a time.Read-onlyGet Web Crawl Job
Get a web crawl job's status and page results, a page at a time. Returns the job with results. Poll until the status is completed or failed.
Inputs
web_crawl_job_idstringrequired- ID of the web crawl job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
batch_sizeinteger- Number of page results per response page. Example: 20.
pageinteger- Page number of results, starting at 1. Example: 1.
hyperbrowser_web_crawl_status_getGet only the status of a web crawl job.Read-onlyGet Web Crawl Job Status
Get only the status of a web crawl job. Returns the status. Use hyperbrowser_web_crawl_get for the pages.
Inputs
web_crawl_job_idstringrequired- ID of the web crawl job. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_web_fetchFetch a web page in a cloud browser and wait for the content as Markdown, HTML, links, a screenshot, JSON or branding data.Read-onlyFetch Web Page
Fetch a web page in a cloud browser and wait for the content as Markdown, HTML, links, a screenshot, JSON or branding data. Returns the content directly. Use it for one page now; use hyperbrowser_scrape_start for async jobs.
Inputs
urlstringrequired- URL of the page to start from. Example: https://example.com/pricing.
browserobject- Browser settings: screen, profileId, solveCaptchas and location. Example: {"screen": {"width": 1440, "height": 900}}
cacheobject- Cache settings: maxAgeSeconds to accept a cached copy up to that age. Example: {"maxAgeSeconds": 3600}
navigationobject- Navigation settings: waitUntil (load, domcontentloaded, networkidle), timeoutMs and waitFor. Example: {"waitUntil": "load", "timeoutMs": 30000}
outputsobject- Output settings: formats (markdown, html, links, screenshot, json, branding), sanitize, includeSelectors and excludeSelectors. Example: {"formats": ["markdown"]}
stealthstring- Stealth level: none, auto or ultra. Example: auto.one of
noneautoultra
hyperbrowser_web_searchRun a web search with optional location and filters (site, file type, title or URL terms, exact phrase).Read-onlySearch the Web
Run a web search with optional location and filters (site, file type, title or URL terms, exact phrase). Returns results with titles, URLs and descriptions. Use hyperbrowser_web_fetch to read a result.
Inputs
querystringrequired- Search query. Example: best browser automation tools 2026.
filtersobject- Search filters: site, excludeSite, filetype, intitle, inurl, exactPhrase, excludeTerms and boostTerms. Example: {"site": "github.com"}
locationobject- Location to search from: country, state and city. Example: {"country": "US"}
max_age_secondsinteger- Accept cached results up to this age in seconds. Example: 86400.
pageinteger- Page number of results, starting at 1. Example: 1.
hyperbrowser_browser_use_task_startStart a task that the open-source Browser Use agent runs in a cloud browser from natural-language instructions.WriteStart Browser Use Task
Start a task that the open-source Browser Use agent runs in a cloud browser from natural-language instructions. Returns a task ID and the live-view URL; get the result with hyperbrowser_browser_use_task_get. Tasks are billed per step. Other agents: hyperbrowser_hyper_agent_task_start, hyperbrowser_browser_use_task_start, hyperbrowser_claude_computer_use_task_start, hyperbrowser_openai_cua_task_start, hyperbrowser_gemini_computer_use_task_start.
Inputs
taskstringrequired- Natural-language instructions for the agent. Example: Go to news.ycombinator.com and return the titles of the top 3 stories.
keep_browser_openboolean- Set to true to keep the session open after the task ends. Example: false.
llmstring- Model that runs the agent. Example: gpt-4o.one of
gpt-4ogpt-4o-minigpt-4.1gpt-4.1-miniclaude-sonnet-5claude-sonnet-4-6claude-haiku-5-5gemini-2.0-flashgemini-2.5-flashgemini-4-hydrogengemini-3.8-flash max_actions_per_stepnumber- Maximum browser actions per agent step. Example: 5.
max_failuresnumber- Maximum consecutive failures before the task stops. Example: 3.
max_stepsnumber- Maximum number of agent steps. Example: 20.
message_contextstring- Extra context for the agent, such as facts it should know. Example: Prices are listed in USD.
session_idstring- ID of an existing browser session to run in, from hyperbrowser_session_create; a new session is created when empty. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
use_visionboolean- Set to true to let the agent use screenshots. Example: true.
validate_outputboolean- Set to true to have the agent check its own output before finishing. Example: false.
versionstring- Agent version to run; defaults to the latest. Example: 0.1.40.one of
0.1.400.7.10latest
hyperbrowser_claude_computer_use_task_startStart a task that Anthropic Claude computer use runs in a cloud browser from natural-language instructions.WriteStart Claude Computer Use Task
Start a task that Anthropic Claude computer use runs in a cloud browser from natural-language instructions. Returns a task ID and the live-view URL; get the result with hyperbrowser_claude_computer_use_task_get. Tasks are billed per step. Other agents: hyperbrowser_hyper_agent_task_start, hyperbrowser_browser_use_task_start, hyperbrowser_claude_computer_use_task_start, hyperbrowser_openai_cua_task_start, hyperbrowser_gemini_computer_use_task_start.
Inputs
taskstringrequired- Natural-language instructions for the agent. Example: Go to news.ycombinator.com and return the titles of the top 3 stories.
keep_browser_openboolean- Set to true to keep the session open after the task ends. Example: false.
llmstring- Model that runs the agent. Example: claude-opus-5-5.one of
claude-opus-5-5claude-fable-5-2claude-fable-5-1claude-opus-5claude-opus-4-5claude-opus-4-6claude-opus-4-7claude-opus-4-8claude-haiku-5-5claude-haiku-4-5-20251001claude-sonnet-5-5claude-sonnet-5claude-sonnet-4-6 max_failuresnumber- Maximum consecutive failures before the task stops. Example: 3.
max_stepsnumber- Maximum number of agent steps. Example: 20.
reasoning_effortstring- Reasoning effort for the model. Example: medium.one of
lowmediumhighxhighmax session_idstring- ID of an existing browser session to run in, from hyperbrowser_session_create; a new session is created when empty. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
use_computer_actionboolean- Set to true to drive the browser through the computer action endpoint. Example: false.
hyperbrowser_crawl_startStart crawling a website from a URL, following links up to max_pages, and scrape each page.WriteStart Crawl Job
Start crawling a website from a URL, following links up to max_pages, and scrape each page. Returns a job ID; get the pages with hyperbrowser_crawl_get. Use hyperbrowser_web_crawl_start for the newer web crawl API with fetch-style outputs.
Inputs
urlstringrequired- URL of the page to start from. Example: https://example.com/pricing.
exclude_patternsarray- URL path patterns to skip. Example: ["/blog/*"]
follow_linksboolean- Set to true to follow links found on crawled pages. Example: true.
ignore_sitemapboolean- Set to true to skip the site's sitemap when discovering pages. Example: false.
include_patternsarray- URL path patterns to crawl; other pages are skipped. Example: ["/docs/*"]
max_pagesinteger- Maximum number of pages to crawl. Example: 10.
scrape_optionsobject- Scrape settings: formats (html, links, markdown, screenshot), onlyMainContent, includeTags, excludeTags, waitFor, timeout and waitUntil. Example: {"formats": ["markdown", "links"], "onlyMainContent": true}
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
hyperbrowser_extract_startStart extracting structured data from one or more URLs with an AI model, guided by a prompt and/or a JSON Schema.WriteStart Extract Job
Start extracting structured data from one or more URLs with an AI model, guided by a prompt and/or a JSON Schema. Returns a job ID; get the data with hyperbrowser_extract_get. A URL ending in /* also follows links on that site.
Inputs
urlsarrayrequired- URLs of the pages to process. Example: ["https://example.com/pricing", "https://example.com/about"]
max_linksnumber- Maximum number of links to follow when a URL ends with /*. Example: 5.
promptstring- What to extract from the pages. Example: Extract every plan name with its monthly price.
schemaobject- JSON Schema the extracted data must follow. Example: {"type": "object", "properties": {"plans": {"type": "array", "items": {"type": "object", "properties": {"name": {"type": "string"}, "price": {"type": "string...
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
system_promptstring- System prompt for the extraction model. Example: You extract pricing data from SaaS websites.
wait_fornumber- Milliseconds to wait after page load before extracting. Example: 2000.
hyperbrowser_gemini_computer_use_task_startStart a task that Google Gemini computer use runs in a cloud browser from natural-language instructions.WriteStart Gemini Computer Use Task
Start a task that Google Gemini computer use runs in a cloud browser from natural-language instructions. Returns a task ID and the live-view URL; get the result with hyperbrowser_gemini_computer_use_task_get. Tasks are billed per step. Other agents: hyperbrowser_hyper_agent_task_start, hyperbrowser_browser_use_task_start, hyperbrowser_claude_computer_use_task_start, hyperbrowser_openai_cua_task_start, hyperbrowser_gemini_computer_use_task_start.
Inputs
taskstringrequired- Natural-language instructions for the agent. Example: Go to news.ycombinator.com and return the titles of the top 3 stories.
keep_browser_openboolean- Set to true to keep the session open after the task ends. Example: false.
llmstring- Model that runs the agent. Example: gemini-4-hydrogen.one of
gemini-4-hydrogengemini-4-carbongemini-4-argongemini-3.8-flashgemini-3.7-flashgemini-3.6-flashgemini-3.5-flashgemini-3.5-flash-litegemini-3-flash-previewgemini-2.5-computer-use-preview-10-2025 max_failuresnumber- Maximum consecutive failures before the task stops. Example: 3.
max_stepsnumber- Maximum number of agent steps. Example: 20.
reasoning_effortstring- Reasoning effort for the model. Example: medium.one of
minimallowmediumhighxhigh session_idstring- ID of an existing browser session to run in, from hyperbrowser_session_create; a new session is created when empty. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
use_computer_actionboolean- Set to true to drive the browser through the computer action endpoint. Example: false.
hyperbrowser_hyper_agent_task_startStart a task that Hyperbrowser's own browser agent runs in a cloud browser from natural-language instructions.WriteStart HyperAgent Task
Start a task that Hyperbrowser's own browser agent runs in a cloud browser from natural-language instructions. Returns a task ID and the live-view URL; get the result with hyperbrowser_hyper_agent_task_get. Tasks are billed per step. Other agents: hyperbrowser_hyper_agent_task_start, hyperbrowser_browser_use_task_start, hyperbrowser_claude_computer_use_task_start, hyperbrowser_openai_cua_task_start, hyperbrowser_gemini_computer_use_task_start.
Inputs
taskstringrequired- Natural-language instructions for the agent. Example: Go to news.ycombinator.com and return the titles of the top 3 stories.
keep_browser_openboolean- Set to true to keep the session open after the task ends. Example: false.
llmstring- Model that runs the agent. Example: gpt-5.5.one of
gpt-6.1-terragpt-6-lunagpt-5.6-lunagpt-5.5gpt-5.2gpt-5.1gpt-5gpt-5-minigpt-4ogpt-4o-minigpt-4.1gpt-4.1-miniclaude-sonnet-5claude-sonnet-4-6claude-haiku-5-5gemini-2.5-flashgemini-4-hydrogengemini-3.8-flashgemini-3.7-flashgemini-3-flash-preview max_stepsnumber- Maximum number of agent steps. Example: 20.
session_idstring- ID of an existing browser session to run in, from hyperbrowser_session_create; a new session is created when empty. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
versionstring- Agent version to run; defaults to the latest. Example: 1.1.0.one of
0.8.01.1.0
hyperbrowser_openai_cua_task_startStart a task that OpenAI's computer-using agent (CUA) runs in a cloud browser from natural-language instructions.WriteStart OpenAI CUA Task
Start a task that OpenAI's computer-using agent (CUA) runs in a cloud browser from natural-language instructions. Returns a task ID and the live-view URL; get the result with hyperbrowser_openai_cua_task_get. Tasks are billed per step. Other agents: hyperbrowser_hyper_agent_task_start, hyperbrowser_browser_use_task_start, hyperbrowser_claude_computer_use_task_start, hyperbrowser_openai_cua_task_start, hyperbrowser_gemini_computer_use_task_start.
Inputs
taskstringrequired- Natural-language instructions for the agent. Example: Go to news.ycombinator.com and return the titles of the top 3 stories.
keep_browser_openboolean- Set to true to keep the session open after the task ends. Example: false.
llmstring- Model that runs the agent. Example: gpt-5.5.one of
computer-use-previewgpt-6-astragpt-6.1-solgpt-6.1-terragpt-6-solgpt-6-lunagpt-5.6-solgpt-5.6-terragpt-5.6-lunagpt-5.5gpt-5.4gpt-5.4-mini max_failuresnumber- Maximum consecutive failures before the task stops. Example: 3.
max_stepsnumber- Maximum number of agent steps. Example: 20.
reasoning_effortstring- Reasoning effort for the model. Example: medium.one of
nonelowmediumhighxhighmax session_idstring- ID of an existing browser session to run in, from hyperbrowser_session_create; a new session is created when empty. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
use_computer_actionboolean- Set to true to drive the browser through the computer action endpoint. Example: false.
hyperbrowser_profile_createCreate a browser profile that stores cookies, local storage and cache between sessions.WriteCreate Profile
Create a browser profile that stores cookies, local storage and cache between sessions. Returns the profile ID. Load it with the profile option of hyperbrowser_session_create.
Inputs
namestring- Name of the profile. Example: checkout-login.
hyperbrowser_profile_forkCopy an existing browser profile into a new one.WriteFork Profile
Copy an existing browser profile into a new one. Returns the new profile ID. Use it to branch a logged-in state without changing the original.
Inputs
profile_idstringrequired- ID of the profile to copy. Example: 5b1c2d3e-4f5a-4b6c-8d7e-9f0a1b2c3d4e.
namestring- Name of the new profile. Example: checkout-login.
hyperbrowser_sandbox_createStart a CPU sandbox (a cloud VM) from an image such as node or python, or from a memory snapshot, with optional CPU, memory, disk, ports, volume mounts and outbound network rules.WriteCreate Sandbox
Start a CPU sandbox (a cloud VM) from an image such as node or python, or from a memory snapshot, with optional CPU, memory, disk, ports, volume mounts and outbound network rules. Returns the sandbox ID and connection details. Stop it with hyperbrowser_sandbox_stop when done.
Inputs
allow_internet_accessboolean- Outbound internet access policy. Example: true.
allow_outarray- Outbound allow rules (IPv4 address, CIDR range, or domain). macOS supports IPv4 addresses and CIDRs only. Example: ["api.github.com"]
deny_outarray- Outbound deny rules (IPv4 address or CIDR range). macOS supports IPv4 addresses and CIDRs only. Example: ["10.0.0.0/8"]
disk_size_mi_binteger- Disk size in MiB for image launches. GPU sandboxes default to and require at least 12288 MiB (12 GiB), with a maximum of 65536 MiB (64 GiB), subject to plan and host limits. GPU disk is ephemeral and files are deleted when the sandbox stops. For macOS, omit this field to use the source disk size; resizing is not supported. Example: 8192.
enable_recordingboolean- Enable recording. For macOS, captures an HLS desktop recording available in the dashboard Recording tab. Example: false.
exposed_portsarray- Ports to expose at launch. Example: [{"port": 8080}]
image_idstring- Pin a specific image revision. Requires imageName. Example: img_7f3a2b.
image_namestring- Image name to launch from. CPU sandboxes can use a base image such as node or python, or a custom image. GPU sandboxes require a GPU-ready image built by your team; wait for gpuImageReady on its build. For macOS, use macos-base with runtimeClass macos; each image launch creates a new writable disk. Example: python.
mem_mi_binteger- System memory (RAM) in MiB for image launches or macOS disk launches. For GPU sandboxes this is separate from GPU memory (VRAM), which is determined by gpu. macOS requires at least 4096 MiB, in multiples of 1024 MiB. Plan and host limits apply. Example: 2048.
mountsobject- Volume mounts, keyed by absolute mount path inside a CPU sandbox. GPU and macOS sandboxes do not support shared volume mounts. Example: {"/data": {"volumeId": "vol_12ab34"}}
regionstring- Region to run in. Example: us.one of
usus-centralus-westus-eastasia-southeurope-west runtime_classstring- Runtime selection. Requests without GPU or macOS options create CPU sandboxes (firecracker). Setting gpu selects gvisor-cpu automatically; omit runtimeClass for GPU creation. Set macos explicitly for a Mac sandbox. Example: firecracker.one of
firecrackergvisor-cpumacos snapshot_idstring- Pin a specific snapshot revision. Requires snapshotName. Example: snap_4c9d1e.
snapshot_namestring- CPU sandbox memory snapshot to restore. GPU sandboxes do not support snapshots; macOS uses diskId instead. Example: warm-python.
timeout_minutesinteger- Maximum lifetime in minutes. Example: 30.
vcpusinteger- vCPU count for image launches or macOS disk launches. macOS requires at least 2 vCPUs; available sizes depend on your plan and host capacity. Example: 2.
hyperbrowser_scrape_batch_startStart scraping a list of URLs in parallel.WriteStart Batch Scrape Job
Start scraping a list of URLs in parallel. Returns a job ID; get the results with hyperbrowser_scrape_batch_get. Use hyperbrowser_scrape_start for a single URL.
Inputs
urlsarrayrequired- URLs of the pages to process. Example: ["https://example.com/pricing", "https://example.com/about"]
scrape_optionsobject- Scrape settings: formats (html, links, markdown, screenshot), onlyMainContent, includeTags, excludeTags, waitFor, timeout and waitUntil. Example: {"formats": ["markdown", "links"], "onlyMainContent": true}
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
hyperbrowser_scrape_startStart scraping one URL in a cloud browser and return its content as Markdown, HTML, links or a screenshot.WriteStart Scrape Job
Start scraping one URL in a cloud browser and return its content as Markdown, HTML, links or a screenshot. Returns a job ID; get the result with hyperbrowser_scrape_get. Use hyperbrowser_web_fetch for a synchronous fetch and hyperbrowser_scrape_batch_start for many URLs.
Inputs
urlstringrequired- URL of the page to start from. Example: https://example.com/pricing.
scrape_optionsobject- Scrape settings: formats (html, links, markdown, screenshot), onlyMainContent, includeTags, excludeTags, waitFor, timeout and waitUntil. Example: {"formats": ["markdown", "links"], "onlyMainContent": true}
session_optionsobject- Browser session settings for the job, such as useStealth, useProxy, proxyCountry, solveCaptchas, adblock, screen and profile (same fields as hyperbrowser_session_create). Example: {"useStealth": true, "solveCaptchas": true, "adblock": true}
hyperbrowser_session_createStart a cloud browser session with optional stealth, proxy, CAPTCHA solving, ad blocking, fingerprint, profile and recording settings.WriteCreate Browser Session
Start a cloud browser session with optional stealth, proxy, CAPTCHA solving, ad blocking, fingerprint, profile and recording settings. Returns the session ID, live-view URL and the CDP/WebSocket endpoint to drive it. Stop it with hyperbrowser_session_stop when done, since sessions are billed while open. Use the scrape, extract or task tools instead when you only need a result.
Inputs
accept_cookiesboolean- Set to true to accept cookie banners automatically. Example: true.
adblockboolean- Set to true to block ads. Example: true.
annoyancesboolean- Set to true to block cookie banners and pop-ups. Example: true.
devicearray- Device types to fingerprint as: desktop or mobile. Example: ["desktop"]
enable_video_web_recordingboolean- Set to true to also record video; enable_web_recording must be true. Example: false.
enable_web_mcpboolean- Set to true to discover and invoke WebMCP tools on pages. Example: false.
enable_web_recordingboolean- Set to true to record the session for replay. Example: true.
extension_idsarray- IDs of uploaded extensions to load, from hyperbrowser_extensions_list. Example: ["a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d"]
localesarray- Browser locales, for example en. Example: ["en"]
operating_systemsarray- Operating systems to fingerprint as: windows, android, macos, linux or ios. Example: ["macos"]
platformarray- Browsers to fingerprint as, for example chrome, firefox, safari or edge. Example: ["chrome"]
profileobject- Saved profile to load: id, plus persistChanges to save cookies and storage back to it. Example: {"id": "5b1c2d3e-4f5a-4b6c-8d7e-9f0a1b2c3d4e", "persistChanges": true}
proxy_citystring- City for the proxy, for example new york; cannot be combined with proxy_state. Example: new york.
proxy_countrystring- Two-letter country code for the proxy. Example: US.one of
ADAEAFALAMAOARATAUAWAZBABDBEBGBHBJBOBRBSBTBYBZCACFCHCICLCMCNCOCRCUCYCZDEDJDKDMECEEEGESETEUFIFJFRGBGEGHGMGRHKHNHRHTHUIDIEILINIQIRISITJMJOJPKEKHKRKWKZLBLILRLTLULVMAMCMDMEMGMKMLMMMNMRMTMUMVMXMYMZNGNLNONZOMPAPEPHPKPLPRPTPYQARANDOM_COUNTRYRORSRUSASCSDSESGSISKSNSSTDTGTHTMTNTRTTTWUAUGUSUYUZVEVGVNYEZAZMZWadaeafalamaoaratauawazbabdbebgbhbjbobrbsbtbybzcacfchciclcmcncocrcucyczdedjdkdmeceeegeseteufifjfrgbgeghgmgrhkhnhrhthuidieiliniqirisitjmjojpkekhkrkwkzlblilrltlulvmamcmdmemgmkmlmmmnmrmtmumvmxmymzngnlnonzompapephpkplprptpyqarorsrusascsdsesgsisksnsstdtgthtmtntrtttwuaugusuyuzvevgvnyezazmzw proxy_statestring- US state code for the proxy; cannot be combined with proxy_city. Example: CA.one of
ALAKAZARCACOCTDEFLGAHIIDILINIAKSKYLAMEMDMAMIMNMSMOMTNENVNHNJNMNYNCNDOHOKORPARISCSDTNTXUTVTVAWAWVWIWYalakazarcacoctdeflgahiidiliniakskylamemdmamimnmsmomtnenvnhnjnmnyncndohokorpariscsdtntxutvtvawawvwiwy regionstring- Region to run in. Example: us.one of
usus-centralus-westus-eastasia-southeurope-west save_downloadsboolean- Set to true to keep files downloaded during the session. Example: false.
screenobject- Screen size as width and height in pixels. Example: {"width": 1440, "height": 900}
solve_captchasboolean- Set to true to solve CAPTCHAs automatically (paid plans). Example: true.
static_ip_idstring- ID of a static IP to use. Example: sip_123.
timeout_minutesnumber- Maximum lifetime in minutes. Example: 30.
trackersboolean- Set to true to block trackers. Example: true.
url_blocklistarray- URL patterns the browser must not load. Example: ["*.doubleclick.net"]
use_proxyboolean- Set to true to route traffic through a residential proxy. Example: false.
use_stealthboolean- Set to true to use stealth mode against bot detection. Example: true.
use_ultra_stealthboolean- Set to true to use ultra stealth mode (paid plans). Example: false.
hyperbrowser_session_webmcp_tool_invokeInvoke a WebMCP tool exposed by a page in a session and wait for the result.WriteInvoke Session WebMCP Tool
Invoke a WebMCP tool exposed by a page in a session and wait for the result. Returns the tool output, or awaiting_submission with an invocation ID for forms. Do not retry blindly if the response is lost, since the tool may have run. Get tool references from hyperbrowser_session_webmcp_tools_list.
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
tool_refstringrequired- Tool reference from hyperbrowser_session_webmcp_tools_list. Example: tool_ref_abc123.
inputobject- Arguments matching the WebMCP tool's input schema. Example: {"query": "blue running shoes"}
timeout_secondsinteger- Tool execution budget in seconds, 1 to 120. Example: 60.
hyperbrowser_volume_createCreate a persistent volume that can be mounted into sandboxes.WriteCreate Volume
Create a persistent volume that can be mounted into sandboxes. Returns the volume ID. Mount it with the mounts option of hyperbrowser_sandbox_create.
Inputs
namestringrequired- Name of the volume. Example: checkout-login.
hyperbrowser_web_crawl_startStart an async crawl that follows links from a URL and returns each page in the requested output formats.WriteStart Web Crawl Job
Start an async crawl that follows links from a URL and returns each page in the requested output formats. Returns a job ID; get the pages with hyperbrowser_web_crawl_get.
Inputs
urlstringrequired- URL of the page to start from. Example: https://example.com/pricing.
browserobject- Browser settings: screen, profileId, solveCaptchas and location. Example: {"screen": {"width": 1440, "height": 900}}
cacheobject- Cache settings: maxAgeSeconds to accept a cached copy up to that age. Example: {"maxAgeSeconds": 3600}
crawl_optionsobject- Crawl settings: maxPages, followLinks, ignoreSitemap, includePatterns and excludePatterns. Example: {"maxPages": 10, "followLinks": true}
navigationobject- Navigation settings: waitUntil (load, domcontentloaded, networkidle), timeoutMs and waitFor. Example: {"waitUntil": "load", "timeoutMs": 30000}
outputsobject- Output settings: formats (markdown, html, links, screenshot, json, branding), sanitize, includeSelectors and excludeSelectors. Example: {"formats": ["markdown"]}
stealthstring- Stealth level: none, auto or ultra. Example: auto.one of
noneautoultra
hyperbrowser_browser_use_task_stopStop a running Browser Use task.DestructiveStop Browser Use Task
Stop a running Browser Use task. Returns the result. The partial result stays available from hyperbrowser_browser_use_task_get.
- Idempotent
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_claude_computer_use_task_stopStop a running Claude Computer Use task.DestructiveStop Claude Computer Use Task
Stop a running Claude Computer Use task. Returns the result. The partial result stays available from hyperbrowser_claude_computer_use_task_get.
- Idempotent
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_gemini_computer_use_task_stopStop a running Gemini Computer Use task.DestructiveStop Gemini Computer Use Task
Stop a running Gemini Computer Use task. Returns the result. The partial result stays available from hyperbrowser_gemini_computer_use_task_get.
- Idempotent
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_hyper_agent_task_stopStop a running HyperAgent task.DestructiveStop HyperAgent Task
Stop a running HyperAgent task. Returns the result. The partial result stays available from hyperbrowser_hyper_agent_task_get.
- Idempotent
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_openai_cua_task_stopStop a running OpenAI CUA task.DestructiveStop OpenAI CUA Task
Stop a running OpenAI CUA task. Returns the result. The partial result stays available from hyperbrowser_openai_cua_task_get.
- Idempotent
Inputs
task_idstringrequired- ID of the task. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_profile_deleteDelete a browser profile and its stored data.DestructiveDelete Profile
Delete a browser profile and its stored data. Returns the result.
- Idempotent
Inputs
profile_idstringrequired- ID of the profile. Example: 5b1c2d3e-4f5a-4b6c-8d7e-9f0a1b2c3d4e.
hyperbrowser_sandbox_stopStop a running sandbox and release its VM.DestructiveStop Sandbox
Stop a running sandbox and release its VM. Returns the result.
- Idempotent
Inputs
sandbox_idstringrequired- ID of the sandbox. Example: sbx_9a8b7c6d.
hyperbrowser_session_stopStop a running browser session and release its browser.DestructiveStop Browser Session
Stop a running browser session and release its browser. Returns the result. Recordings and downloads stay available afterwards.
- Idempotent
Inputs
session_idstringrequired- ID of the session. Example: 8f2c1a7e-4b3d-4e8a-9c21-5d6f7a8b9c0d.
hyperbrowser_volume_deleteDelete a volume and its data by ID or name.DestructiveDelete Volume
Delete a volume and its data by ID or name. Returns the result. A name shared by several volumes returns an error; use the ID then.
- Idempotent
Inputs
volumestringrequired- Volume ID or name. Example: vol_12ab34.
No tools match.