Allows browser automation via Firefox extension bridge for controlling existing browser tabs, including navigation, clicking, typing, and other interactions.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Playwright MCP Server navigate to localhost:3000 and click the login button"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Browser automation via the Model Context Protocol. Supports headless Playwright, Chrome Extension bridge, and Firefox Extension bridge for controlling existing browser tabs.
npm install
npx playwright install chromium
npm run build
node dist/index.jsRelated MCP server: selenium-mcp
Link the MCP agent to your existing browser tabs. Two extensions are provided:
extension/)Uses chrome.debugger API (CDP) for full browser control.
Go to chrome://extensions → Load unpacked → select extension/
Start the MCP server: node dist/index.js
Click the extension icon → Connect
Use extension_* tools
extension-firefox/)Uses WebExtensions API with content scripts (no CDP dependency).
Go to about:debugging#/runtime/this-firefox → Load Temporary Add-on → select extension-firefox/manifest.json
Start the MCP server: node dist/index.js
Click the extension icon → Connect
Use firefox_* tools
Tool | Description |
| Check extension connection status |
| Execute JavaScript in the tab |
| Capture a screenshot of the tab |
| List all open browser tabs |
| Attach to a specific tab by ID |
Tool | Description |
| Navigate the connected tab to a URL |
| Click an element by CSS selector |
Tool | Description |
| Navigate the connected tab to a URL |
| Click an element by CSS selector |
| Type text into an input field |
| Fill an input field with a value |
| Get text content of an element |
| Get HTML content of page or element |
| Hover over an element |
| Select an option in a select element |
| Check a checkbox |
| Uncheck a checkbox |
| Get an attribute value from an element |
| Get the current page URL |
| Get the current page title |
| Navigate back in history |
| Navigate forward in history |
| Reload the current page |
| Scroll the page |
| Take a screenshot of the connected tab |
| Execute JavaScript in the connected tab |
25+ browser_* tools for headless Chromium via Playwright.
Env Var | Default | Description |
|
| WebSocket port for extension bridge |
|
| Set to |
This server cannot be deployed
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Live browser debugging for AI assistants — DOM, console, network via MCP.
Launch, inspect, control, and share isolated cloud browsers for your agents.
