Integration · Developer tools

Connect Claude & ChatGPT to Hyperbrowser

Ask your AI to read a web page, crawl a site or pull structured data out of a set of URLs, using your own Hyperbrowser account. It can search the web, scrape one page or many at once, and start an AI browser agent that clicks through a site to carry out a task. Longer jobs return a job ID, and the AI checks back for the result.

Connect Hyperbrowser free

Free plan, no credit card. Takes about a minute.

Try asking

“Get the content of this pricing page.”
The AI fetches the page directly and returns its content.
“Crawl our docs site, at most 50 pages.”
It starts a crawl job from the URL with a page limit and reads the collected pages as the job runs.
“From these five product pages, pull out name, price and stock status.”
It starts an extract job with your description, optionally with a JSON schema, and returns the structured data when it is done.

What your AI can do

Scrape and crawl

Fetch a single page, scrape one or many URLs, and crawl a site up to a page limit, with output options per job.

Extract and search

Pull structured data out of pages with a prompt and optional JSON schema, and search the web with filters.

Browser agents and sessions

Run a browser agent task in plain words, follow or stop it, stop cloud browser sessions and manage saved profiles.

“Search the web for MCP setup guides, only on dev.to.”
It runs a web search with a site filter and lists the results.
“Scrape these 20 URLs at once.”
It starts a batch scrape job and reads each page's content when the batch is finished.
“Open example.com, find the contact form and tell me which fields it asks for.”
It starts a browser agent task described in plain words, then reads the agent's steps and final result.

85 tools for Hyperbrowser

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

batch_scrape_pagesVisible to othersStart scraping a list of pages at once. Pass `urls` and optional `scrape_options`. Returns a batch job ID.
cancel_buildDeletesCancel a build (build id). Destructive action; may require approval. API summary: Cancel an image build.
crawl_websiteChanges dataStart crawling a website from `url`, following links up to `max_pages`. Returns a crawl job ID.
create_buildChanges dataCreate a new build. Required: image name, input sha256 or input size bytes. API summary: Create an image build.
create_claude_computer_useChanges dataCreate a new claude computer use. Required: task. API summary: Start a claude computer use task.
create_cuaChanges dataCreate a new cua. Required: task. API summary: Start a CUA task.
create_evaluateChanges dataCreate a new evaluate. API summary: Run manual CAPTCHA evaluation.
create_gemini_computer_useChanges dataCreate a new gemini computer use. Required: task. API summary: Start a gemini computer use task.
create_grok_computer_useChanges dataCreate a new grok computer use. Required: task. API summary: Start a grok computer use task.
create_hyper_agentChanges dataCreate a new hyper agent. Required: task. API summary: Start a HyperAgent task.
create_jevChanges dataCreate a new jev. Required: task. API summary: Start a jev computer use task.
create_meta_computer_useChanges dataCreate a new meta computer use. Required: task. API summary: Start a meta computer use task.
create_profileChanges dataCreate a new saved browser profile, optionally with a `name`.
create_sandboxChanges dataCreate a new sandbox. Search sandboxes first to avoid duplicates. API summary: Create new sandbox.
create_sandbox_exposeChanges dataCreate a new expose for a sandbox. Required: port. API summary: Expose a sandbox port.
create_sandbox_snapshotChanges dataCreate a new snapshot for a sandbox. Search snapshots first to avoid duplicates. API summary: Create a sandbox memory snapshot.
create_sandbox_unexposeChanges dataCreate a new unexpose for a sandbox. Required: port. API summary: Remove an exposed sandbox port.
create_volumeChanges dataCreate a new volume. Required: name. Search volumes first to avoid duplicates. API summary: Create a volume.
delete_imageDeletesPermanently delete a image by image key. Destructive action; may require approval. API summary: Delete sandbox image.
delete_profileDeletesPermanently delete a profile by profile id. Destructive action; may require approval. API summary: Delete profile by ID.
delete_snapshotDeletesPermanently delete a snapshot by snapshot key. Destructive action; may require approval. API summary: Delete sandbox snapshot.
delete_volumeDeletesPermanently delete a volume by volume key. Destructive action; may require approval.
extract_dataChanges dataStart extracting structured data from one or more `urls`. Describe what to pull out in `prompt`, and optionally give a JSON `schema` for the result. Returns a job ID.
fetch_a_web_page_with_x402_paymentChanges dataCreate a new fetch. Required: url. API summary: Fetch a web page with X402 payment.
fetch_web_pageChanges dataFetch one web page's content directly and return it. Pass `url` and optionally `outputs` to choose formats and selectors.
get_batch_scrape_resultGet a batch scrape job's status and results. Pass `batch_id`.
get_batch_statusGet the current status of a batch by batch id. API summary: Get batch scrape job status.
get_browser_agent_taskGet a browser agent task's status, steps and final result. Pass `browser_use_id`.
get_browser_use_statusGet the current status of a browser use by browser use id. API summary: Get browser use task status.
get_buildGet one build by build id. API summary: Get image build by ID.
get_claude_computer_useGet one claude computer use by claude computer use id. API summary: Get claude computer use task status and results.
get_claude_computer_use_statusGet the current status of a claude computer use by claude computer use id. API summary: Get claude computer use task status.
get_crawl_resultGet a crawl job's status and the pages collected so far. Pass `crawl_id`, optionally `page` and `batch_size` to page through results.
get_crawl_statusGet the current status of a crawl by crawl id. API summary: Get crawl job status.
get_cuaGet one cua by cua id. API summary: Get CUA task status and results.
get_cua_statusGet the current status of a cua by cua id. API summary: Get CUA task status.
get_extract_resultGet an extract job's status and the extracted data. Pass `extract_id`.
get_extract_statusGet the current status of a extract by extract id. API summary: Get extract job status.
get_gemini_computer_useGet one gemini computer use by gemini computer use id. API summary: Get gemini computer use task status and results.
get_gemini_computer_use_statusGet the current status of a gemini computer use by gemini computer use id. API summary: Get gemini computer use task status.
get_grok_computer_useGet one grok computer use by grok computer use id. API summary: Get grok computer use task status and results.
get_grok_computer_use_statusGet the current status of a grok computer use by grok computer use id. API summary: Get grok computer use task status.
get_hyper_agentGet one hyper agent by hyper agent id. API summary: Get HyperAgent task status and results.
get_hyper_agent_statusGet the current status of a hyper agent by hyper agent id. API summary: Get HyperAgent task status.
get_jevGet one jev by jev id. API summary: Get jev computer use task status and results.
get_jev_statusGet the current status of a jev by jev id. API summary: Get jev computer use task status.
get_meta_computer_useGet one meta computer use by meta computer use id. API summary: Get meta computer use task status and results.
get_meta_computer_use_statusGet the current status of a meta computer use by meta computer use id. API summary: Get meta computer use task status.
get_profileGet one profile by profile id. API summary: Get profile by ID.
get_sandboxGet one sandbox by sandbox id. API summary: Get sandbox by ID.
get_scrape_resultGet a scrape job's status and the page content once finished. Pass `scrape_id`.
get_scrape_statusGet the current status of a scrape by scrape id. API summary: Get scrape job status.
get_sessionGet one cloud browser session's details and status by `session_id`.
get_snapshotGet one snapshot by snapshot key. API summary: Get sandbox snapshot.
get_volumeGet one volume by volume id. API summary: Get volume by ID.
get_web_crawl_job_resultsGet one crawl by crawl id. Results are paginated. API summary: Get web crawl job results.
get_web_crawl_job_statusGet the current status of a crawl by crawl id. API summary: Get web crawl job status.
list_buildsList builds. Optional filters: status. Results are paginated. API summary: Get list of image builds.
list_listsList lists. API summary: List all extensions.
list_profilesList saved browser profiles (kept logins and cookies), optionally filtered by `name`.
list_session_downloads_urlsList downloads urls for a session. API summary: Get session downloads URL.
list_session_recording_urlsList recording urls for a session. API summary: Get session recording URL.
list_session_video_recording_urlsList video recording urls for a session. API summary: Get session video recording URL.
run_browser_agent_taskChanges dataStart an AI browser agent that carries out a task on the web, described in plain words in `task`. Optionally cap `max_steps`. Returns a task ID. The agent can click, type and submit forms on sites.
scrape_pageChanges dataStart scraping one web page. Pass `url` and optionally `scrape_options` (output formats, tags to include or exclude, wait time). Returns a job ID; fetch the content with get_scrape_result.
search_imagesSearch images by source or search. Use this to find existing images before creating a new image. Results are paginated. API summary: Get list of sandbox images.
search_sandboxesSearch sandboxes by status, start, end or search. Use this to find existing sandboxes before creating a new sandbox. Results are paginated. API summary: Get list of sandboxes.
search_snapshotsSearch snapshots by image name, status or search. Use this to find existing snapshots before creating a new snapshot. Results are paginated. API summary: Get list of sandbox snapshots.
search_the_web_with_x402_paymentChanges dataSearch webs. Use this to find existing webs before creating a new web. API summary: Search the web with X402 payment.
search_volumesSearch volumes by search. Use this to find existing volumes before creating a new volume. Results are paginated. API summary: Get list of volumes.
search_webChanges dataSearch the web for `query`. Optional `filters` (site, words in title or URL, excluded terms) and `location` narrow results.
start_a_web_crawl_jobChanges dataCreate a new crawl. Required: url. API summary: Start a web crawl job.
stop_browser_agent_taskVisible to othersStop a running browser agent task. Pass `browser_use_id`.
stop_sessionVisible to othersStop a cloud browser session by `session_id`.
submit_buildVisible to othersComplete a build (build id). Has effects visible outside this system. API summary: Complete an image build upload.
update_claude_computer_use_stopsVisible to othersUpdate an existing stop identified by claude computer use id. Has effects visible outside this system. API summary: Stop a claude computer use task.
update_cua_stopsVisible to othersUpdate an existing stop identified by cua id. Has effects visible outside this system. API summary: Stop a CUA task.
update_gemini_computer_use_stopsVisible to othersUpdate an existing stop identified by gemini computer use id. Has effects visible outside this system. API summary: Stop a gemini computer use task.
update_grok_computer_use_stopsVisible to othersUpdate an existing stop identified by grok computer use id. Has effects visible outside this system. API summary: Stop a grok computer use task.
update_hyper_agent_stopsVisible to othersUpdate an existing stop identified by hyper agent id. Has effects visible outside this system. API summary: Stop a HyperAgent task.
update_jev_stopsVisible to othersUpdate an existing stop identified by jev id. Has effects visible outside this system. API summary: Stop a jev computer use task.
update_meta_computer_use_stopsVisible to othersUpdate an existing stop identified by meta computer use id. Has effects visible outside this system. API summary: Stop a meta computer use task.
update_sandbox_networksVisible to othersUpdate an existing network identified by sandbox id. Has effects visible outside this system. API summary: Update sandbox network policy.
update_sandbox_stopsVisible to othersUpdate an existing stop identified by sandbox id. Has effects visible outside this system. API summary: Stop a sandbox.
update_session_updatesVisible to othersUpdate an existing update identified by session id. Has effects visible outside this system. API summary: Update a running session.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Hyperbrowser from the app list.
2
Paste your key
Paste your Hyperbrowser API key. Sign in to the Hyperbrowser dashboard at app.hyperbrowser.ai and copy your API key, or create a new one under API keys.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Hyperbrowser?

The AI can fetch and scrape web pages, run batch scrapes and crawls, extract structured data, search the web and start browser agent tasks. It can read the status and results of those jobs, stop an agent task or a cloud browser session, and list and create saved browser profiles.

Does the AI see my Hyperbrowser API key?

No. Your Hyperbrowser API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, for example scraping and search without browser agents. A browser agent can click, type and submit forms on real sites, so starting one can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your HeyMyApps link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

HeyMyApps has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Hyperbrowser account.

Why do some jobs return an ID instead of a result?

Scrapes, batch scrapes, crawls, extracts and browser agent tasks run as jobs in Hyperbrowser. The AI starts the job, gets a job ID and then reads the status and results with the matching get tool. fetch_web_page is the exception and returns a page's content directly.