Skip to content

Actions

Kelly Ferrone edited this page Sep 10, 2026 · 5 revisions

Actions

Every action is an MCP tool and an HTTP endpoint with the same parameters. A test fails the build if one exists without the other.

Tool Endpoint Does
open_session POST /browser/open Start a browser session. Do this first.
navigate POST /browser/navigate Go to a URL. Returns the resulting URL and page title.
interact POST /browser/interact Perform a mouse action on an element.
write POST /browser/write Type text into an input, textarea or contenteditable.
press_key POST /browser/press-key Press a named key, at an element or wherever focus currently is.
extract POST /browser/extract Read an element's visible text and innerHTML.
screenshot POST /browser/screenshot Capture a PNG of the page and return it as an image you can see.
save_pdf POST /browser/pdf Print the current page to PDF and keep it with the session's files.
execute_script POST /browser/script Run JavaScript in the page and return its result.
frame POST /browser/frame Move into an iframe, or back out of it.
dialog POST /browser/dialog Answer a native alert, confirm or prompt dialog.
resize POST /browser/resize Resize the browser window.
upload_file POST /browser/upload Attach a file to a file input.
end_browser POST /browser/end Quit the browser and free its Grid slot. Do this when finished.

Over HTTP session_id is always required. Over MCP it depends on whether the server can identify you — see Sessions.


Installing · Deployment · Administration

Clone this wiki locally