CI Release npm version Chrome Extension License: MIT

👆 MCP Pointer

Point to browser DOM elements for agentic coding tools via MCP!

MCP Pointer is a local tool combining an MCP Server with a Chrome Extension:

1. 🖥️ MCP Server (Node.js package) - Bridges between the browser and AI tools via the Model Context Protocol
2. 🌐 Chrome Extension - Captures DOM element selections in the browser using Option+Click

The extension lets you visually select DOM elements in the browser, and the MCP server makes this textual context available to agentic coding tools like Claude Code, Cursor, and Windsurf through standardized MCP tools.

✨ Features

• 🎯 Option+Click Selection - Simply hold Option (Alt on Windows) and click any element
• 📋 Complete Element Data - Text content, CSS classes, HTML attributes, positioning, and styling
• 💡 Dynamic Context Control - Request visible-only text, suppress text entirely, or dial CSS detail from none → full computed styles per MCP call
• ⚛️ React Component Detection - Component names and source files via Fiber (experimental)
• 🔗 WebSocket Connection - Real-time communication between browser and AI tools
• 🤖 MCP Compatible - Works with Claude Code and other MCP-enabled AI tools

🎬 Usage example (video)

https://github.com/user-attachments/assets/98c4adf6-1f05-4c9b-be41-0416ab784e2c

See MCP Pointer in action: Option+Click any element in your browser, then ask your agentic coding tool about it (in this example, Claude Code). The AI gets complete textual context about the selected DOM element including CSS properties, url, selector, and more.

🚀 Getting Started

1. Install Chrome Extension

🎉 Now available on Chrome Web Store!

Install from Chrome Web Store

Simply click the link above to install from the Chrome Web Store.

2. Configure MCP Server

One command setup for your AI tool:

npx -y @mcp-pointer/server config claude  # or cursor, windsurf, and others - see below

# For other AI tools
npx -y @mcp-pointer/server config cursor     # Opens Cursor deeplink for automatic installation
npx -y @mcp-pointer/server config windsurf   # Automatically updates Windsurf config file
npx -y @mcp-pointer/server config manual     # Shows manual configuration for other tools

After configuration, restart your coding tool to load the MCP connection.

🔄 Already using MCP Pointer? Run the config command again to update to auto-updating configuration:

npx -y @mcp-pointer/server config <your-tool>  # Reconfigures to always use latest version

3. Start Using

1. Navigate to any webpage
2. Option+Click any element to select it
3. Ask your AI to analyze the targeted element!

Your AI tool will automatically start the MCP server when needed using the npx -y @mcp-pointer/server@latest start command.

Available MCP Tool:

• get-pointed-element – Returns textual information about the currently pointed DOM element. Optional arguments:
  • textDetail: 0 | 1 | 2 (default 2) controls how much text to include (0 = none, 1 = visible text only, 2 = visible + hidden).
  • cssLevel: 0 | 1 | 2 | 3 (default 1) controls styling detail, from no CSS (0) up to full computed styles (3).

🎯 How It Works

1. Element Selection: Content script captures Option+Click events
2. Data Extraction: Analyzes element structure, CSS, and framework info
3. WebSocket Transport: Sends data to MCP server on port 7007
4. MCP Protocol: Makes data available to AI tools via MCP tools
5. AI Analysis: Your assistant can now see and analyze the element!

🎨 Element Data Extracted

• Basic Info: Tag name, ID, classes, text content
• CSS Properties: Display, position, colors, dimensions
• Component Info: React component names and source files (experimental)
• Attributes: All HTML attributes
• Position: Exact coordinates and dimensions
• Source Hints: File paths and component origins

🔍 Framework Support

• ⚛️ React - Component names and source files via Fiber (experimental)
• 📦 Generic HTML/CSS/JS - Full support for any web content
• 🔮 Planned - Vue component detection (PRs appreciated)

🌐 Browser Support

• ✅ Chrome - Full support (tested)
• 🟡 Chromium-based browsers - Should work (Edge, Brave, Arc - load built extension manually)

🐛 Troubleshooting

Extension Not Connecting

1. Make sure MCP server is running: npx -y @mcp-pointer/server@latest start
2. Check browser console for WebSocket errors
3. Verify port 7007 is not blocked by firewall

MCP Tools Not Available

1. Restart your AI assistant after installing
2. Check MCP configuration: mcp-pointer config <your-tool>
3. Verify server is running: npx -y @mcp-pointer/server@latest start

Elements Not Highlighting

1. Some pages block content scripts (chrome://, etc.)
2. Try refreshing the page
3. Check if targeting is enabled (click extension icon)

🚀 Roadmap

1. Dynamic Context Control

• Full raw context transferred to server
• LLM-configurable detail levels (visible text only, all text, CSS levels)
• Progressive refinement options / token-conscious data fetching

2. Visual Content Support (for multimodal LLMs)

• Base64 encoding for images (img tags)
• Screenshot capture of selected elements
• Separate MCP tool for direct visual content retrieval

3. Enhanced Framework Support

• Vue.js component detection
• Better React support (React 19 removed _debugSource, affecting source mapping in dev builds)

4. Multi Select

• Having the ability to select multiple DOM elements
• https://github.com/etsd-tech/mcp-pointer/pull/9

📝 License

MIT License - see LICENSE file for details

🤝 Contributing

We welcome contributions! Please see our CONTRIBUTING.md guide for development setup and guidelines.

Inspired by tools like Click-to-Component for component development workflows.

Made with ❤️ for AI-powered web development

Now your AI can analyze any element you point at with Option+Click! 👆