The catalogue/Browserbase
Browserbase
app.browserbase
Cloud browser automation with stealth, CAPTCHA solving, and Live View
Version2.0.0
Categorydevelopment
AuthAPI key
Tools15
Transportstdio
LicenceMIT
01
What it does
The app, in its own words.
Cloud browser automation at scale. Anti-bot bypass, CAPTCHA solving, residential proxies, session recording, and parallel browsers. Includes Live View to watch the browser in real time.
02
Tools
15 tools the agent can call.
Every one is declared with typed parameters and returns structured results, so the host can render them instead of narrating them.
- clickClick on an element in the page.
- evaluateExecute JavaScript in the page context.
- fill-formFill multiple form fields at once.
- get-contentGet the current page HTML or plain text content.
- navigateNavigate the browser to a URL.
- navigate-backGo back to the previous page.
- network-requestsList network requests made in the current session.
- press-keyPress a keyboard key.
- session-closeClose a Browserbase session and release cloud resources.
- session-createCreate a new Browserbase cloud browser session. Returns a sessionId to use with all other tools, and opens a Live View window so you can watch the browser in real time.
- session-listList all active Browserbase sessions in this instance.
- snapshotCapture an accessibility snapshot of the current page. Returns the page structure with element refs for interaction.
- take-screenshotTake a screenshot of the current page. Saved to /workspace/ on the shared volume.
- typeType text into an editable element.
- wait-forWait for text to appear/disappear on the page, or wait a fixed amount of time.
03
Auth and permissions
What it asks for.
Declared in the manifest, in advance. The app cannot reach anything it did not ask for here.
User secrets
BROWSERBASE_API_KEYBROWSERBASE_PROJECT_ID
Reading further
The manifest and the source for Browserbase live in the monorepo, alongside the other apps.