Automate browser interactions for web scraping, testing, and navigation. Use when the user needs to visit a webpage, interact with UI elements, take screenshots, or extract content from rendered pages.
Control Chrome browser to navigate pages, interact with elements, capture screenshots, and extract content.
browserAll browser interactions go through the browser tool with an action parameter.
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| action | string | Yes | One of: navigate, snapshot, screenshot, click, type, press, inspect, evaluate, wait. |
| url | string | Conditional | URL to navigate to. Required for navigate. |
| selector | string | Conditional | CSS selector. Required for click and type. |
| text | string | Conditional | Text to type. Required for type. |
| key | string | Conditional | Key name. Required for press. |
| script | string | Conditional | JavaScript expression. Required for evaluate. |
| seconds | integer | No | Seconds to wait (default: 2). |
| max_chars | integer | No | Max characters for snapshot (default: 50000). |
| headless | boolean | No | Run in headless mode (default: false). |
Load a URL in the browser.
browser(action="navigate", url="https://example.com")
Discover interactive elements on the current page. Returns up to 50 visible elements with their CSS selectors, type, and label. Always use this after navigating to find selectors for click/type.
browser(action="inspect")
Return the visible text content of the page (document.body.innerText).
browser(action="snapshot")
Capture a PNG screenshot of the current viewport.
browser(action="screenshot")
Click on an element by CSS selector.
browser(action="click", selector="#submit-button")
browser(action="click", selector="[aria-label='Search']")
Type text into an input field by CSS selector. Clicks to focus first, then types character by character.
browser(action="type", selector="input[name='q']", text="search query")
Press a special key: Enter, Tab, Escape, Backspace, Delete, ArrowUp, ArrowDown, ArrowLeft, ArrowRight, Home, End, Space.
browser(action="press", key="Enter")
browser(action="press", key="Escape")
Execute JavaScript in the page context and return the result.
browser(action="evaluate", script="document.title")
browser(action="evaluate", script="window.scrollTo(0, document.body.scrollHeight)")
Wait for a specified number of seconds.
browser(action="wait", seconds=3)
innerText, or running custom JS.headless=true for background tasks that don't need a visible window.Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer