Overview
Browser tools give the agent a full Chromium browser it can control programmatically. This is useful for pages that require JavaScript to render, login flows, form submission, and visual verification via screenshots. Browser tools are in the Full tier - they are only sent to frontier models (Claude, GPT-4o, Gemini) that can reliably reason about page state and UI interactions.Browser tools require Puppeteer to be installed. Run
pnpm install to install all optional dependencies, including Puppeteer.Available Tools
Tool Details
browser_navigate
Navigate to a URL. Opens a new browser page if none is active.
string
required
Full URL to navigate to. Must be
http:// or https://.string
default:"networkidle2"
Wait condition:
load, domcontentloaded, networkidle0, networkidle2.number
default:"30000"
Navigation timeout in milliseconds.
browser_snapshot
Get the current page’s accessibility tree as structured text. More token-efficient than a screenshot for text-heavy pages.
Include hidden elements in the snapshot.
browser_click
Click an element on the page.
string
required
CSS selector for the element to click. Use
aria/Button Name for accessible selectors.string
default:"left"
Mouse button:
left, right, middle.number
default:"1"
Number of clicks (use 2 for double-click).
browser_type
Type text into an input or textarea.
string
required
CSS selector for the input element.
string
required
Text to type.
boolean
default:"false"
Clear existing content before typing.
number
default:"0"
Delay between keystrokes in milliseconds (simulates human typing).
browser_screenshot
Capture the current page as a PNG image.
boolean
default:"false"
Capture the full scrollable page, not just the viewport.
string
Capture only a specific element instead of the whole page.
number
default:"80"
JPEG quality (1-100). Only applies when format is
jpeg.browser_pages
List all currently open browser pages/tabs.
Returns page IDs, URLs, and titles. Use page IDs to target operations at specific tabs.
browser_close
Close a specific page or all browser pages.
string
ID of the specific page to close. Omit to close all pages.
Typical Workflow
1
Navigate to the page
2
Take a snapshot to see the page structure
3
Fill in the login form
4
Click the submit button
5
Screenshot to verify the result
Safe vs Full Browser Tools
By default, only “safe” browser tools (browser_snapshot, browser_screenshot, browser_pages) are included for non-frontier models. The full automation set requires a frontier model to reason about page state accurately.
Related Tools
Web Fetch
Faster for APIs and static pages that do not need JavaScript.
Web Search
Search without opening a full browser session.