BrowserGenie

Load a web page in the browser. Use this whenever you need to go to a specific website or web address. Automatically waits for page to load.

{
  "tool": "navigate_to_url",
  "arguments": {
    "url": "…"
  }
}

Go back to the previous page in browser history. Use this instead of navigating to the previous URL directly when possible.

{
  "tool": "navigate_back",
  "arguments": {
    "tabId": 0,
    "apiKey": "…"
  }
}

Go forward to the next page in browser history. Only works if you previously navigated back.

{
  "tool": "navigate_forward",
  "arguments": {
    "tabId": 0,
    "apiKey": "…"
  }
}

Refresh the current page. Use this if the page seems stuck, outdated, or needs fresh data.

{
  "tool": "navigate_reload",
  "arguments": {
    "ignoreCache": true,
    "tabId": 0,
    "apiKey": "…"
  }
}

Get a list of ALL open browser tabs. Use this to find tab IDs, see what pages are open, or locate a specific website you need to interact with. Returns tab ID, URL, title, and active status.

{
  "tool": "list_tabs",
  "arguments": {
    "apiKey": "…"
  }
}

Switch to a specific tab. Use this when you need to interact with a different open tab. Makes the tab active and brings its window to front.

{
  "tool": "select_tab",
  "arguments": {
    "tabId": 0
  }
}

Open a brand new browser tab. You can optionally provide a URL to navigate to immediately. Returns the new tab ID so you can interact with it.

{
  "tool": "new_tab",
  "arguments": {
    "url": "…",
    "apiKey": "…"
  }
}

Close a specific browser tab. Use this to clean up tabs you no longer need. Be careful - closed tabs cannot be recovered through this tool!

{
  "tool": "close_tab",
  "arguments": {
    "tabId": 0
  }
}

Capture URL, title, and a DOM hash for quick tab state comparison. Useful for verifying cross-tab state sync.

{
  "tool": "get_tab_state",
  "arguments": {
    "tabId": 0,
    "apiKey": "…"
  }
}

Verify two tabs have the same state (URL, title, DOM hash). Useful for cross-tab state sync testing.

{
  "tool": "assert_tabs_match",
  "arguments": {
    "tabIdA": 0,
    "tabIdB": 0
  }
}

Test cross-tab localStorage synchronization. Sets a value in tab A and checks if it appears in tab B.

{
  "tool": "test_storage_sync",
  "arguments": {
    "tabIdA": 0,
    "tabIdB": 0,
    "key": "…",
    "value": "…"
  }
}

Press a single keyboard key with optional modifiers. Use this for special keys: Enter, Tab, Escape, arrows, function keys, or keyboard shortcuts. Does NOT type text - use type_text for that.

{
  "tool": "press_key",
  "arguments": {
    "key": "…"
  }
}

Type regular text into the currently focused input field. Use this for typing usernames, passwords, search queries, form data, etc. Each character is typed individually like a real user.

{
  "tool": "type_text",
  "arguments": {
    "text": "…"
  }
}

Take a screenshot of what's currently visible in the browser window. Uses CDP Page.captureScreenshot by default so modals and high-z-index overlays stack correctly — prior versions rendered the underlying drawer and hid modals. Falls back to chrome.tabs.captureVisibleTab when CDP is unavailable. Use `saveTo` to write the image to a file on disk instead of (or in addition to) returning it inline.

{
  "tool": "screenshot_viewport",
  "arguments": {
    "format": "png",
    "quality": 0,
    "method": "auto"
  }
}

Take a screenshot of the ENTIRE page, including content you need to scroll down to see. Automatically scrolls and stitches images together. The original scroll position is restored after capture so the page state is unchanged. Use this when you need to see everything on the page. Use `saveTo` to write the image to a file on disk.

{
  "tool": "screenshot_full_page",
  "arguments": {
    "format": "png",
    "quality": 0,
    "saveTo": "…"
  }
}

Take a screenshot of a specific element only. Provide a CSS selector or XPath to capture just that element. Use `saveTo` to write the image to a file on disk.

{
  "tool": "screenshot_element",
  "arguments": {
    "selector": "…"
  }
}

Click on any element on the page. Use this for buttons, links, checkboxes, dropdowns, or any interactive element. Simulates real human mouse behavior with Bézier curve movement, randomized delays, and natural press/release timing.

{
  "tool": "click_element",
  "arguments": {
    "target": {}
  }
}

One-stop tool for filling text-based form fields. Automatically clicks the input, clears existing text, types your text, and optionally submits with Enter. Use this for search boxes, login forms, registration fields, etc. IMPORTANT: This tool only works for text inputs, textareas, and contenteditable elements. It will NOT work for file uploads — use set_input_files for those.

{
  "tool": "input_and_type",
  "arguments": {
    "selector": "…",
    "text": "…"
  }
}

Type into a server-side autocomplete / combobox (Ant Design AutoComplete, MUI Autocomplete, Headless UI Combobox, etc.) and click the matching dropdown option. Use this instead of `input_and_type` + Enter when the component only accepts values selected from its dropdown (pressing Enter on free-text either submits the wrong filter or clears the field).

{
  "tool": "select_from_autocomplete",
  "arguments": {
    "selector": "…",
    "text": "…"
  }
}

Drag an element from one location to another. Use this for sliders, sortable lists, file upload drop zones, or any drag-interactive elements. Simulates realistic human drag speed.

{
  "tool": "drag_and_drop",
  "arguments": {
    "from": {},
    "to": {}
  }
}