Playwright browser automation for testing, scraping, and web interaction. Control a pre-configured Chromium browser with full page interaction, screenshot capture, form filling, and JavaScript execution. Each user gets isolated browser sessions with automatic cleanup.
This MCP server bundle is compatible with any MCP client including Claude Desktop, Cursor, and other Model Context Protocol implementations.
Click an element on the page. Supports single/double/triple clicks, right-click, and keyboard modifiers. Waits for element to be actionable before cli...
Evaluate JavaScript expression on the page or specific element. Returns the result of the expression. Useful for extracting data, modifying page state...
Returns all network requests made since the current page was loaded. Includes URL, method, status, headers, and timing. Useful for debugging API calls...
Perform drag and drop operation between two elements. Drags source element and drops it onto target element. Useful for drag-and-drop interfaces, sort...
Resize the browser window to specified dimensions. Useful for testing responsive designs, simulating different screen sizes, or capturing screenshots ...
Capture accessibility snapshot of the current page. Returns structured tree of page elements with role, name, and value attributes. Better than screen...
Navigate back to the previous page in browser history. Returns navigation result with URL and title after going back. Does nothing if there is no prev...
Take a screenshot of the current page or specific element. Returns base64-encoded image data. Use for visual verification, documentation, or debugging...
Fill multiple form fields at once. Faster than browser_type for forms as it sets values directly. Automatically clears existing values before filling....
Handle browser dialogs like alert, confirm, and prompt. Can accept or dismiss the dialog, and provide text for prompts. Must be set up before the dial...
Press a key or key combination on the keyboard. Supports special keys (Enter, Escape, Tab) and modifiers (Control, Shift, Alt, Meta). Optionally focus...
Upload one or multiple files to a file input element. Supports single and multiple file inputs. Files must be accessible from the server filesystem wh...
Hover over an element on the page. Useful for triggering hover states, dropdowns, tooltips, and other hover-based interactions. Waits for element to b...
Wait for text to appear or disappear on the page, or wait for a specified amount of time. Useful for waiting for dynamic content, loading states, or i...
Type text into an editable element character by character. Focuses the element first, then types with optional delay between keystrokes. Triggers all ...
Manage browser tabs - list all tabs, create new tabs, close tabs, or switch between tabs. Essential for multi-page workflows and parallel browsing tas...
Returns all console messages (log, warn, error) from the current page since it was loaded. Useful for debugging JavaScript errors, tracking applicatio...
Navigate to a URL in the browser. Returns navigation result with final URL (after redirects), page title, and status. Use this as the starting point f...
Connect this Browser Tools MCP server to any MCP client in minutes
Compatible with Claude Desktop, Cursor, and all Model Context Protocol clients
Model Context Protocol lets AI tools call external capabilities securely through a single URL. This bundle groups tools behind an MCP endpoint that many clients can use.
Skip the manual setup! Use the .mcpb
file format for one-click installation. Check the Claude Desktop tab for setup instructions.
Select ChatGPT, Cursor, Claude Code, or another tab for copy-paste config.