Launch a Chrome/Chromium browser with CDP enabled. Creates a dedicated profile directory.

Connect to an already-running Chrome/Chromium instance with CDP enabled.

List all open browser tabs.

Navigate to a URL or perform navigation actions (back, forward, refresh).

Discover interactive elements on the page (inputs, buttons, links, etc.).

Interact with elements: click, type, upload files, select options, etc.

Read content from the page: full page text, element text, attributes.

Capture a screenshot of the page or a specific element.

Wait for conditions: element visible, text contains, navigation, etc.

Execute JavaScript in the page context.

List all frames on the page (main frame + iframes). Use this to find iframes for LinkedIn Easy Apply, Gmail compose, etc.

Interact with elements inside iframes. Automatically searches all frames for the element.

Type text at the current cursor position using CDP Input.insertText. This simulates real keyboard input and works with React/Vue/Angular controlled inputs. Focus an element first with cdp_interact focus action.

Click at raw x,y screen coordinates. Useful for clicking elements in shadow DOM or other hard-to-select elements. Get coordinates from screenshots or cdp_find_elements rect values.

Upload a file to a file input in shadow DOM. First use cdp_execute to find the file input and store it in window.__fileInput, then call this tool.

Set the value of an input/textarea, properly handling React/Vue/Angular controlled inputs. This clears existing content and sets new value, triggering all necessary events. Best for form fields that cdp_interact type struggles with.

Interact with Monaco Editor (VS Code web editor) on the page. Detects Monaco instances and provides reliable get/set operations that preserve formatting. Much better than generic text input tools for Monaco.

Submit a form reliably, with special handling for React/Vue/Angular. Tries multiple submission methods: requestSubmit(), clicking submit button, dispatching submit event, and direct submit(). Works when Enter key fails.

Scan current page structure and store in site memory. Detects iframes, shadow DOM, forms, and key elements. Automatically skips if already scanned this conversation epoch (compaction resets this). Use force=true to rescan anyway.

Get stored site memory for the current page or a specific domain. Returns iframe locations, shadow DOM elements, and interaction patterns learned from previous visits.

Add a note or selector pattern to site memory. Use this to record what you learned about interacting with a site.

List all sites in memory with their key info.

Clear site memory for a domain (forces fresh scan next time).

Get current epoch info. Useful for debugging site memory behavior.

Track a bug in the CDP-MCP. Writes to BUGS.md in the cdp-mcp folder. Use this when you encounter issues with browser automation.

List all tracked bugs in CDP-MCP.

Mark a bug as fixed and remove it from the tracking file.