Open main or support, or reopen one as somebody else.

main is your own identity: its page, cookies, fingerprint, logins. support is a helper beside it for what must not touch that identity - a temporary mailbox for a verification, a lookup the site must not connect to the account. They share nothing. support is yours to manage: open it when the task needs a second identity, and close it with browser_close as soon as the task no longer needs it, before you answer. It is not saved.

Called on a browser that is already up, this REOPENS it with the settings given, and what it held is gone.

seed the identity; same seed, same fingerprint. Left out, one is drawn. profile a directory keeping cookies, logins and the seed between opens; "" means none. proxy the exit, http://user:pass@host:port or socks5://host:port; "" means this machine's own address; left out for support, it shares the exit main has.

Close one browser and free what it was holding.

The page it had is gone with it. The other browser is not touched.

Closing FORGETS who that browser was: opening it again is a new stranger, not the same person resumed. That is deliberate - a browser somebody shut down should not come back wearing its old identity.

Which of the two browsers are open, where each one is, and which one the commands that name none go to.

Answers JSON: focus, limit, note, and browsers - each with id, running, focused, url (the page it is on) and urls (every page it holds, which is more than one only when a site opened one). A browser that is not running has been declared and has not been needed yet; the next command aimed at it starts it as the same person.

Starts nothing: it reports what is running, so asking is free.

Who is browsing right now: the identity, the exit, the profile and the page.

Ask whenever you need to know which person the browser currently is, or from where its traffic leaves. The seed is what you would pass to browser_open to become this person again, so this is also how you record an identity worth repeating.

It starts nothing. If no browser is running yet it says so, because until one is running there is no identity to report.

browser is main unless you say support, and they share nothing.

Go to a url in this browser's page, opening it if none exists.

Answers with the HTTP status the server gave and the url actually landed on, which is not always the one asked for: a redirect to a login wall or a regional domain shows up here. Read the status before trusting the page - a 404 or a 403 still has a document, and reading it as content is the mistake this reply exists to prevent.

wait_until is "domcontentloaded" by default, which returns as soon as the markup is parsed. Use "load" when the page needs its images and stylesheets, or "networkidle" for a single-page app that fetches its content after load.

browser is main unless you say support, and they share nothing.

The visible text of an element, with the markup gone.

The cheapest way to read a page. Narrow the selector when you know where the answer is; use browser_read_html instead when the structure matters, or browser_snapshot when you need something to click.

Long text is cut at max_chars (6000 by default) and the cut is marked in what comes back, so text that ends without that marker is the whole thing.

browser is main unless you say support, and they share nothing.

Title, url, and the interactive elements that are actually visible.

Each element carries a selector when one can reach it: pass that string to browser_click or browser_type VERBATIM. It is built to match exactly one element, which the obvious selector often does not - measured across 958 elements on real pages, 88% could be addressed but only 48% unambiguously, and Playwright acts on the first match, so a caller aiming at the third of five identical links would silently hit the first.

Elements with no selector carry at, the centre coordinates, for browser_click_at.

Not the accessibility tree: on a real sign-up page a single country <select> contributes about two hundred <option> nodes, which fill the character cap before the form the caller was looking for appears at all.

browser is main unless you say support, and they share nothing.

The page's HTML, cleaned down to what is worth reading.

Use this when the STRUCTURE matters - a form and its labels, a table, what a control is wired to. browser_snapshot gives a flat inventory of things to click; this keeps the markup and the relationships inside it.

mode="form" keeps the interactive surface and the text explaining it, mode="text" returns the prose alone, mode="full" keeps the structure with the noise and the attribute soup removed.

Unlike browser_read_text this is NOT capped: it returns the whole reduced page, tens of thousands of characters on a large one. Cutting markup in the middle leaves tags that mean nothing, so it is not cut - but the answer can be long. Reach for browser_snapshot when you only need something to click.

browser is main unless you say support, and they share nothing.

One screenshot of this browser's page, on demand.

browser is main unless you say support, and they share nothing.

The whole browser window as a person at the machine sees it: tab strip, address bar, the page and the pointer, from a live capture kept running on that page. For watching the work, not for acting on it: the picture is window pixels, so do not feed its coordinates to browser_click_at; use browser_take_screenshot for that.

Starts nothing. A browser that is not running has no window, so this refuses rather than opening one to photograph: a look is not a command, and the live panes call this many times a second.

browser is main unless you say support, and they share nothing.

Click the first element matching a CSS selector.

Scrolls it into view and waits for it to be clickable. When no selector can describe the target, use browser_click_at with coordinates from browser_snapshot.

browser is main unless you say support, and they share nothing.

Click (or press-and-hold) a raw viewport coordinate instead of a selector - for targets a selector cannot reliably reach: a slider track, a canvas-drawn captcha, a precise point inside a wider element. Moves the pointer there first (no teleport), then down, then up, holding first if hold_seconds is set. Returns a screenshot taken right after release.

Coordinates are relative to the VIEWPORT, not to the page, so the ones in a snapshot go stale the moment anything scrolls. Nothing raises when that happens: the click lands on whatever is at that spot now. Take a fresh snapshot after anything that could have moved the page, and prefer browser_click with the element's selector whenever it has one.

browser is main unless you say support, and they share nothing.

Fill a field, replacing whatever it holds.

This sets the value rather than typing key by key, so it will not fire the per-keystroke handlers an autocomplete needs. For those, click the field and use browser_press_key.

browser is main unless you say support, and they share nothing.

Choose an option in a dropdown (<select>), by its visible label or by its value.

Use this rather than clicking the dropdown and pressing arrow keys: a click plus arrows cannot tell you which row it landed on, and setting the value through browser_evaluate changes it without the page seeing a real interaction.

browser is main unless you say support, and they share nothing.

Press a key on whatever has focus: "Enter", "Tab", "Escape", "ArrowDown", "Control+a", or a single character.

browser is main unless you say support, and they share nothing.

READ from the page with JavaScript and get the result as JSON.

For what the other tools cannot see: a computed style, a value held in a framework's state, the length of a list.

Acting on the page is refused, and the refusal names the tool to use. Assigning to value, checked or selected, or calling click(), dispatchEvent(), submit() or requestSubmit(), changes the page without a real keystroke or pointer, and a page can tell. Use browser_click, browser_type or browser_select_option instead; they do the same thing through the pointer and the keyboard. Reading any of those properties is fine.

The refusal catches the obvious spellings, not every possible one. A script that slips past it is still the wrong way to do the thing: report it in your answer rather than using it.

browser is main unless you say support, and they share nothing.