jfeammnjpkecdekppnclgkkffahnhfhe
Automate your Browser using Cursor, Claude, VS Code. More capable and context efficient than Playwright MCP. Control your browser via MCP. Automate your browser tasks with AI. Like Playwright MCP but via extension. less context window usage. 10x more capable via full CDP support 1. **Install the Chrome Extension** Install the [Playwriter MCP Extension](https://github.com/remorses/playwriter) from the Chrome Web Store (or load it unpacked during development). Pin the extension to your Chrome toolbar for easy access. Click the Playwriter MCP extension icon on any tab you want to control. The icon will turn green when successfully connected. **Icon states:** - **Gray:** Not connected - **Green:** Connected and ready - **Orange badge (...):** Connecting - **Red badge (!):** Error 3. **Add MCP to Your Agent** Add the following configuration to your MCP client settings (e.g., Claude Desktop's `claude_desktop_config.json`): Restart your MCP client and you're ready to go! Your AI assistant can now control the browser through the extension. ### Using the MCP **Important:** Before using the MCP, you must enable the extension on at least one tab: 1. Pin the Playwriter extension to your Chrome toolbar (click the puzzle icon) 2. Navigate to a tab you want to control 3. Click the extension icon - it will turn green when connected Once enabled on one or more tabs, your AI assistant can: - Control all enabled tabs through the `execute` tool - Switch between tabs using playwright's context and page APIs - Create new tabs programmatically - Run any Playwright code against your browser tabs The MCP will automatically start a relay server and connect to your enabled browser tabs. ### Using with Playwright You can use playwriter programmatically with playwright-core: const context = browser.contexts()[0] const page = context.pages()[0] await page.goto('https://example.com') await page.screenshot({ path: 'screenshot.png' }) Playwriter uses a Chrome extension instead of launching a full new Chrome window. This approach has several benefits: - **Collaborate with your agent** - Work alongside the AI in the same browser, helping it when stuck on captchas or complex interactions - **Start on existing pages** - Launch the MCP on a page in your existing browser to replicate bugs exactly as they occur - **Reuse your extensions** - Keep using ad blockers, password managers, and other extensions you already have installed - **Bypass automation detection** - Disable CDP/automation temporarily by disconnecting the extension to bypass detection systems like Google login, then reconnect to continue automation. With Playwright's headless Chrome, automation is always detected and blocks your workflow - **Less resource usage** - No need to spawn a separate Chrome instance, saving memory and CPU - **Single browser workflow** - Everything happens in your main Chrome browser, no switching between windows Playwriter has access to the full playwright API available, it can send any CDP command via the playwright methods. It only uses 1 tool `execute` to send playwright code snippets. This means that the LLM can reuse its knowledge about playwright and less context window is used to expose browser automations tools. Playwriter is also more capable because it exposes the full playwright API instead of only a few tools. For comparison here are the tools supported by BrowserMCP: - `browsermcp_browser_navigate` - Navigate to a URL - `browsermcp_browser_go_back` - Go back to the previous page - `browsermcp_browser_go_forward` - Go forward to the next page Page Inspection: - `browsermcp_browser_snapshot` - Capture accessibility snapshot of the current page (use this to get references to elements) - `browsermcp_browser_screenshot` - Take a screenshot of the current page - `browsermcp_browser_get_console_logs` - Get console logs from the browser Interactions: - `browsermcp_browser_click` - Click on an element (requires element reference from snapshot) - `browsermcp_browser_hover` - Hover over an element - `browsermcp_browser_type` - Type text into an editable element (with optional submit) - `browsermcp_browser_select_option` - Select an option in a dropdown - `browsermcp_browser_press_key` - Press a key on the keyboard Utilities: - `browsermcp_browser_wait` - Wait for a specified time in seconds Playwriter is designed with security in mind, ensuring that only you can control your browser. 1. **Local WebSocket Server**: When the MCP starts, it launches a singleton WebSocket server on `localhost:19988` 2. **Dual Connection**: Both the Chrome extension and MCP client connect to this local server 3. **User-Controlled Access**: The extension can only control tabs where you explicitly clicked the extension icon (green icon indicates connected tabs) 4. **Localhost-Only**: The WebSocket server does not send CORS headers, preventing any web pages or remote servers from connecting to it - only processes running on your local machine can establish a connection 5. **Explicit Consent**: Chrome displays an "automation banner" on controlled tabs, making it obvious when a tab is being automated - **Only enabled tabs**: Tabs you explicitly connected by clicking the extension icon - **New tabs created by automation**: Tabs created programmatically through Playwright commands - **Nothing else**: Other browser tabs, your browsing history, or any tabs you haven't explicitly connected remain inaccessible - **No remote access**: External websites or servers cannot connect to the WebSocket (localhost-only) - **No passive monitoring**: The extension cannot read or monitor tabs you haven't connected - **No automatic spreading**: The debugger won't automatically attach to new tabs you open manually This architecture ensures that browser automation only happens with your explicit permission on tabs you choose.
supermemory
Browser extension for the supermemory app Supermemory is an AI tool that enables you to have "SuperMemory" of everything you save, do and talk about - whether it's blogs, videos, or any website. With supermemory, you can connect your context across all popular chatbots and apps seamlessly. You can also chat with your memories on your preferred AI chat app, and use your memories wherever you are.
Nanobrowser: AI Web Agent & Automation
Automate web tasks with AI! NanoBrowser is an open-source Chrome extension that lets you extract data, fill forms, and more. An open-source and local-first web automation agent that runs in your browser. 1️⃣ 100% Free: No subscription fees or hidden costs. Just install and use your own API keys 2️⃣ Privacy-Focused: Agent runs in your local browser instead of cloud 3️⃣ Flexible LLM Options: Supports SOTA LLM models as well as local models 4️⃣ Fully Open Source: Complete transparency in how your browser is automated ✅ Multi-agent System: Specialized agents collaborate to accomplish complex web tasks. ✅ Interactive Side Panel: Intuitive chat interface with real-time status updates. ✅ Task Automation: Seamlessly automate repetitive tasks across websites. ✅ Follow-up Questions: Ask contextual follow-up questions about completed tasks. ✅ Conversation History: Easily access and manage your interaction history. ✅ Multiple LLM Support: Connect your preferred LLM providers and assign different models to different agents. ⚠️ While Nanobrowser may work on some Chromium-based browsers, they are not officially tested and supported. 1️⃣ Click the Nanobrowser icon in your toolbar to open the sidebar. 2️⃣ Click the Settings icon (top right). 3️⃣ Add your preferred LLM API keys. 4️⃣ Choose which model to use for different agents (Navigator, Planner, Validator). 5️⃣ Send your commands to Nanobrowser 1️⃣ Go to TechCrunch and extract top 10 headlines from the last 24 hours 2️⃣ Look for the trending Python repositories on GitHub with most stars 3️⃣ Find a portable Bluetooth speaker on Amazon with a water-resistant design, under $50. It should have a minimum battery life of 10 hours We are open source. We need your help to make Nanobrowser even better! Contributions of all kinds are welcome: 1️⃣ Share prompts & use cases in our Discord server 2️⃣ Create issues or even submit pull requests on our Github repository ❤️ Loving Nanobrowser? Leave us a review on the Chrome Web Store and help others discover this powerful extension! Your support means everything to us.
Web MCP: Browser MCP Service, AI Automated Operations
Launch Browser MCP Service with One Click, Empowering AI to Automate Tasks for You. ✨ Web MCP Service: One-Click Connect AI to Your Browser ✨ Say goodbye to complex code and commands! With just a single click, launch the Web MCP (Model Context Protocol) service on your current browser. Empower AI applications 🤖 that support the MCP protocol, such as VS Code and Claude, to interact directly with your browser, allowing AI to automatically perform tasks like web browsing, information extraction, and content filling. - Real-time Browser Control: Seamlessly replace the Playwright MCP server, enabling AI to directly control your currently used browser instead of launching separate automation windows. - Security at Your Fingertips 🔒: Start, stop, or restart the MCP service at any time, giving you complete control over access and effectively protecting your browsing activity and data privacy. - Stable and Private Connection 🔗: Supports connecting via your local network or your self-deployed proxy service, ensuring stable and private data transmission. * Security First: Never share your Web MCP service link with any untrusted third parties, as this may lead to malicious control of your browser. Please keep it safe! * Risk Disclaimer: AI operations may contain errors or not meet expectations. Please supervise the tasks performed by AI, and users are responsible for any potential risks or losses that may arise from AI operations.
Playwright Extension
Connect your browser to AI agents through Playwright MCP server and CLI. Enables AI-driven web testing, debugging, and automation. Playwright Chrome Extension The Playwright Chrome Extension lets you connect your browser’s active tabs and logged-in sessions to Playwright. With this extension, the Playwright CLI, the Playwright MCP server, and AI agents can interact with real web pages using your actual browser state—cookies, profiles, and authenticated sessions—without re-authenticating or using separate test profiles. Once installed, the extension enables seamless browser automation from local Playwright tools that drive real browser actions (navigation, clicks, form fills, etc.) against the pages you already have open. Reuse your real browser state — no extra logins required. Works with the Playwright CLI for scripted automation and testing. Works with the Playwright MCP server for AI-driven workflows and agents. Ideal for developers, testers, and AI workflows that need realistic browser context. How It Works Install the extension and run Playwright locally with the `--extension` flag — either through the Playwright CLI or the Playwright MCP server. When your automation script or AI client connects, it routes commands through the extension into your open browser tabs, letting tools perform real interactions with pages you’re signed into.
