Integration · Developer tools

Connect Claude & ChatGPT to Anchor Browser

Ask your AI to read a page that needs JavaScript, collect data from a website, or take a screenshot of a page. It runs web tasks in plain language in Anchor's cloud browser, starts and controls browser sessions, and saves pages as PDFs. You can also check usage and answer the agent when it needs a human.

Connect Anchor Browser free

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

Try asking

“Get the text of this pricing page. It only loads with JavaScript.”
The AI opens the URL in a cloud browser and returns the page content.
“Go to this shop page and collect every product name and price.”
It runs a web task from your prompt and returns the data in the shape you asked for.
“Take a full-page screenshot of our homepage.”
It captures the URL at full height, with an optional width and wait time.

What your AI can do

Web tasks in plain language

Run a web task from a prompt, create reusable tasks with input and output schemas, and check their status and results.

Browser sessions

Start sessions with saved profiles, open URLs, click, type, take screenshots and list tabs, downloads and recordings.

Pages, PDFs and usage

Fetch page content, take screenshots, save pages as PDFs, and read billing usage and session history.

“Save this article as a landscape PDF.”
It renders the URL as a PDF, with paper size, margins and landscape if you want them.
“Start a session with my saved profile and open our admin page.”
It starts a cloud browser session with the saved profile, gives you the live view link and opens the URL.
“Is any session waiting for me?”
It lists sessions where the agent needs a human, for example for a login step, and passes on your answer so it can continue.

129 tools for Anchor Browser

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

click_in_sessionChanges dataClick in a browser session by `session_id`, either on a CSS `selector` or at `x`/`y` coordinates.
create_agent_accessChanges dataCreate a new agent access. Required: token or answer. API summary: Create Agent Access project.
create_applicationChanges dataCreate a new application. Required: source. Search applications first to avoid duplicates. API summary: Create Application.
create_application_auth_flowChanges dataCreate a new auth flow for a application. Required: name or methods. API summary: Create Authentication Flow.
create_application_tokenDeletesCreate a new token for a application. Required: callback url. Destructive action; may require approval. API summary: Create Identity Token.
create_batch_sessionVisible to othersCreate a new batch session. Required: count. Has effects visible outside this system. API summary: Create Batch Sessions.
create_batch_session_retryVisible to othersCreate a new retry for a batch session. Has effects visible outside this system. API summary: Retry Failed Batch Sessions.
create_double_clickChanges dataCreate a new double click. Required: x or y. API summary: Mouse Double Click.
create_downChanges dataCreate a new down. Required: x or y. API summary: Mouse Down.
create_event_waitChanges dataCreate a new wait for a event. API summary: Wait for Event.
create_execute_codeChanges dataCreate a new execute code. Required: code. API summary: Execute Code Snippet.
create_identityChanges dataCreate a new identity. Required: source. Search identities first to avoid duplicates. API summary: Create Identity.
create_identity_reauthenticateChanges dataCreate a new reauthenticate for a identity. API summary: Reauthenticate Identity.
create_integrationChanges dataCreate a new integration. Required: name, type or credentials. API summary: Create Integration.
create_moveChanges dataCreate a new move. Required: x or y. API summary: Mouse Move.
create_or_update_task_draft_legacyChanges dataCreate a new task for a task. Required: code. API summary: Create or Update Task Draft (Legacy).
create_pauseChanges dataCreate a new pause. API summary: Pause Session Recording.
create_pause_postChanges dataCreate a new pause. API summary: Pause Agent.
create_profileChanges dataCreate a new profile. Required: name. API summary: Create Profile.
create_resumeChanges dataCreate a new resume. API summary: Resume Session Recording.
create_resume_postChanges dataCreate a new resume. API summary: Resume Agent.
create_reusable_taskChanges dataCreate a reusable browser task from a plain-language `task_prompt` with a `task_name`, optional `input_schema` and `output_schema`. Returns a task ID to run with run_reusable_task.
create_session_clipboardChanges dataCreate a new clipboard for a session. Required: text. API summary: Set Clipboard Content.
create_session_drag_and_dropChanges dataCreate a new drag and drop for a session. Required: start x, start y, end x or end y.
create_session_pasteChanges dataCreate a new paste for a session. Required: text. API summary: Paste Text.
create_session_scrollChanges dataCreate a new scroll for a session. Required: x, y or delta y.
create_shortcutChanges dataCreate a new shortcut. Required: keys. API summary: Keyboard Shortcut.
create_task_2Changes dataCreate a new task for a task. API summary: Deploy Task (Legacy).
create_task_legacyChanges dataCreate a new task. Required: name or language. API summary: Create Task (Legacy).
create_upChanges dataCreate a new up. Required: x or y. API summary: Mouse Up.
create_volumeChanges dataCreate a new volume. Required: name. API summary: Create Volume.
create_volume_directoryChanges dataCreate a new directory for a volume. Required: path. API summary: Create Directory.
create_webhookDeletesCreate a new webhook. Required: url or subscribed events. Destructive action; may require approval. API summary: Create Webhook.
create_webhook_rotate_secretDeletesCreate a new rotate secret for a webhook. Destructive action; may require approval. API summary: Rotate Webhook Signing Secret.
delete_allsMoves moneyPermanently delete a all. Financial or irreversible action; may require approval. API summary: End All Sessions.
delete_applicationDeletesPermanently delete a application by application id. Destructive action; may require approval. API summary: Delete Application.
delete_application_auth_flowDeletesPermanently delete a auth flow by auth flow id. Destructive action; may require approval. API summary: Delete Authentication Flow.
delete_batch_sessionMoves moneyPermanently delete a batch session by batch id. Financial or irreversible action; may require approval. API summary: Delete Batch Sessions.
delete_certificateDeletesPermanently delete a certificate by name. Destructive action; may require approval. API summary: Delete Certificate.
delete_extensionDeletesPermanently delete a extension by extension id. Destructive action; may require approval. API summary: Delete Extension.
delete_identityDeletesPermanently delete a identity by identity id. Destructive action; may require approval. API summary: Delete Identity.
delete_integrationDeletesPermanently delete a integration by integration id. Destructive action; may require approval. API summary: Delete Integration.
delete_profileDeletesPermanently delete a profile by name. Destructive action; may require approval. API summary: Delete Profile.
delete_session_recordingDeletesPermanently delete a recording by recording id. Destructive action; may require approval. API summary: Delete Session Recording.
delete_session_tagsMoves moneyPermanently delete a tag by session id. Financial or irreversible action; may require approval. API summary: Delete Session Tags.
delete_taskDeletesPermanently delete a task by task id. Destructive action; may require approval. API summary: Delete Task (Legacy).
delete_task_version_legacyDeletesPermanently delete a task by task version. Destructive action; may require approval. API summary: Delete Task Version (Legacy).
delete_volumeDeletesPermanently delete a volume by volume id. Destructive action; may require approval. API summary: Delete Volume.
delete_volume_documentsMoves moneyPermanently delete a document by volume id. Financial or irreversible action; may require approval. API summary: Delete Files.
delete_webhookDeletesPermanently delete a webhook by webhook id. Destructive action; may require approval. API summary: Delete Webhook.
download_documentDownload the document for a document. API summary: Download File.
end_sessionDeletesEnd a running browser session by `session_id` and stop its billing.
fetch_webpageChanges dataOpen a `url` in a cloud browser and return the page content. Works for pages that need JavaScript.
get_appendixGet one appendix by appendix ref. API summary: Agent Access challenge data.
get_applicationGet one application by application id. API summary: Get Application.
get_batch_sessionGet one batch session by batch id. API summary: Get Batch Session Status.
get_billing_usageGet billing usage between `from_date` and `to_date`, grouped by `granularity` (hour, day, week, month).
get_by_nameGet one by name by name. API summary: Get Volume By Name.
get_extensionGet one extension by extension id. API summary: Get Extension Details.
get_identityGet one identity by identity id. API summary: Get Identity.
get_latest_task_version_legacyList tasks for a task. API summary: Get Latest Task Version (Legacy).
get_profileGet one profile by name. API summary: Get Profile.
get_sessionGet one browser session by `session_id` with its status, settings and usage.
get_session_historyGet session usage history over time between `from_date` and `to_date`, grouped by `granularity`.
get_session_start_statusCheck a session start request by `request_id` and get the new session ID and live view link once ready.
get_stateGet one state by session id. API summary: Get Dynamic Auth Flow State.
get_taskGet one task by task id. API summary: Get Task Metadata (Legacy).
get_task_draft_legacyList tasks for a task. API summary: Get Task Draft (Legacy).
get_task_execution_result_legacyGet one task for a task by task id 2. API summary: Get Task Execution Result (Legacy).
get_task_generation_statusCheck whether a reusable task (`task_id`) has finished being generated and is ready to run.
get_task_run_statusGet the status and result of a reusable task run by `run_id`.
get_task_version_legacyGet one task by task version. API summary: Get Task Version (Legacy).
get_volumeGet one volume by volume id. API summary: Get Volume.
get_web_task_statusCheck an asynchronous web task by `workflow_id` and get its result once finished.
get_webhookGet one webhook by webhook id. API summary: Get Webhook.
list_active_sessionsList the currently running browser sessions, filterable by `tags`, `profile_name`, `domains` or creation time.
list_agent_accessesList agent accesses. API summary: Agent Access guide.
list_application_auth_flowsList auth flows for a application. API summary: List Application Authentication Flows.
list_batch_sessionsList batch sessions. Optional filters: status, created after or created before. Results are paginated.
list_certificatesList certificates.
list_challengesList challenges. API summary: Get Agent Access challenge.
list_documentsList documents. API summary: List Agent Resources.
list_extensionsList extensions.
list_fetchesList fetches. API summary: Get Session Recording.
list_integrationsList integrations.
list_pending_interventionsList sessions where the AI agent is waiting for a human (for example to solve a login step).
list_profilesList saved browser profiles (stored logins and cookies) that sessions can reuse.
list_requested_human_interventionsList requested human interventions. API summary: Get Requested Human Interventions.
list_session_clipboardsList clipboards for a session. API summary: Get Clipboard Content.
list_session_downloadsList files downloaded during a browser session by `session_id`.
list_session_pagesList the open tabs (pages) of a browser session by `session_id`.
list_session_recordingsList video recordings of a browser session by `session_id`.
list_session_tagsList tags for a session. API summary: Get Session Tags.
list_statsList stats. Optional filters: path. API summary: Get File Info.
list_task_executions_legacyList tasks for a task. Optional filters: status or version. Results are paginated. API summary: List Task Executions (Legacy).
list_task_versions_legacyList tasks for a task. API summary: List Task Versions (Legacy).
list_tasks_legacyList tasks. Results are paginated. API summary: List Tasks (Legacy).
list_volume_documentsList documents for a volume. Optional filters: path or recursive. Results are paginated. API summary: List Files.
list_volume_pathsList paths for a volume. Optional filters: prefix. Results are paginated. API summary: List All Paths.
list_volumesList volumes. Optional filters: include deleted or state.
list_webhook_eventsList events for a webhook. Optional filters: status, event type, since, until or include payload. Results are paginated. API summary: List Webhook Deliveries.
list_webhooksList webhooks.
open_url_in_sessionChanges dataNavigate an open browser session (`session_id`) to `url`.
publish_task_version_legacyChanges dataUpdate an existing task identified by task version. API summary: Publish Task Version (Legacy).
respond_to_interventionChanges dataAnswer an agent's request for human help in session `session_id` with `response` (and the `request_id` if given) so it can continue.
run_reusable_taskChanges dataRun a reusable task by `task_id` with its `input_params`; `sync` true waits for the result, otherwise check with get_task_run_status.
run_task_legacyChanges dataCreate a new task. Required: task id. API summary: Run Task (Legacy).
run_web_taskChanges dataHave an AI agent do a task on the web in plain language (`prompt`), optionally starting at `url` and returning data shaped by `output_schema`. With `async` true it returns an ID to check with get_web_task_status.
save_page_as_pdfChanges dataRender a `url` as a PDF, with optional paper size, margins, `landscape` and header/footer.
screenshot_sessionTake a screenshot of what a running browser session (`session_id`) currently shows.
search_application_identitiesSearch identities for a application by search or metadata. Use this to find existing identities before creating a new identity. API summary: List Application Identities.
search_applicationsSearch applications by search. Use this to find existing applications before creating a new application. API summary: List Applications.
send_testDeletesSend a test (webhook id). Destructive action; may require approval. API summary: Send Test Event.
start_browser_sessionChanges dataStart a cloud browser session, optionally with an `initial_url`, timeout, recording, proxy or a saved profile in `browser`/`session`. Returns a request ID to check with get_session_start_status.
submit_sessionVisible to othersCopy a session (session id). Has effects visible outside this system. API summary: Copy Selected Text.
take_screenshotChanges dataTake a screenshot of a `url`, with optional `width`, `height`, `wait` time and full-page capture (`capture_full_height`).
type_in_sessionChanges dataType `text` into the focused field of a browser session by `session_id`.
update_application_auth_flowChanges dataUpdate an existing auth flow identified by auth flow id. Only the fields you pass are changed. API summary: Update Authentication Flow.
update_batch_sessionVisible to othersUpdate an existing batch session identified by batch id. Only the fields you pass are changed. Has effects visible outside this system. API summary: Update Batch Session.
update_eventChanges dataUpdate an existing event identified by event name. API summary: Signal Event.
update_finalizeVisible to othersUpdate an existing finalize identified by session id. Has effects visible outside this system. API summary: Finalize Dynamic Auth Flow.
update_identityChanges dataUpdate an existing identity identified by identity id. API summary: Update Identity.
update_resolveChanges dataUpdate an existing resolve identified by session id. API summary: Resolve Dynamic Auth Flow Step.
update_session_tagsVisible to othersUpdate an existing tag identified by session id. Has effects visible outside this system. API summary: Put Session Tags.
update_startChanges dataUpdate an existing start identified by session id. API summary: Start Dynamic Auth Flow.
update_taskChanges dataUpdate an existing task identified by task name. API summary: Run Task by Name (Legacy).
update_task_metadata_legacyChanges dataUpdate an existing task identified by task id. API summary: Update Task Metadata (Legacy).
update_webhookDeletesUpdate an existing webhook identified by webhook id. Only the fields you pass are changed. Destructive action; may require approval. API summary: Update Webhook.
upload_document_urlChanges dataUpload a document (volume id). API summary: Create Upload URL.

Set up in three steps

1
Pick the app
Create a free HeyMyApps account and choose Anchor Browser from the app list.
2
Paste your key
Paste your Anchor API key. Sign in to Anchor at app.anchorbrowser.io, open the API key page and copy your API key.
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 Anchor Browser?

It can run web tasks in plain language, fetch page content, take screenshots, save pages as PDFs, and create and run reusable tasks. It can start, control and end browser sessions, answer requests for human help, and read sessions, profiles, downloads, recordings, billing usage and session history.

Does the AI see my Anchor API key?

No. Your Anchor 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. Starting sessions, running tasks and clicking or typing in a session can require your approval, and so can ending a session. 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 Anchor account. Browser usage is billed by Anchor, and the AI can show you that usage.

What happens when the browser agent gets stuck?

Some steps, like a login, need a person. The AI can list sessions where the agent is waiting for a human and pass on your answer so the task can continue. You can also take a screenshot of the session to see what it shows.