Web Viewer MCP Server
Allows AI agents to control and interact with VS Code webviews by providing tools for navigation, element interaction, and state retrieval. It facilitates automated tasks like clicking elements, inputting text, and reading the DOM structure within a VS Code tab.
README
Web Viewer - VS Code Extension Template
VS Code extension template để hiển thị webview với tích hợp MCP Server cho AI agent.
Tính năng
- 📱 Web Viewer: Hiển thị HTML/SPA trong VS Code tab
- 🤖 MCP Server: Standalone server cho AI agent (Claude, Cursor, Gemini)
- 🔧 Tools: Open, close, navigate, click, input, get state
- 📦 Resources: State, DOM structure
Cài đặt
npm install
npm run build
Scripts
| Script | Mô tả |
|---|---|
npm run build |
Build tất cả (webview + extension) |
npm run build:webview |
Build webview bằng Vite |
npm run dev:webview |
Watch mode cho webview |
npm run compile |
Compile TypeScript extension |
Chạy Extension
- Mở project trong VS Code
- Nhấn
F5để chạy Extension Development Host - Chạy command
Open Web viewertừ Command Palette
MCP Server
Tools
| Tool | Mô tả |
|---|---|
web_open |
Mở tab Web viewer |
web_close |
Đóng tab Web viewer |
web_navigate |
Navigate đến route |
web_click |
Click element theo CSS selector |
web_input |
Nhập text vào input field |
web_get_state |
Lấy state hiện tại |
Resources
| URI | Mô tả |
|---|---|
spa://state |
Current state (URL, title, forms, links) |
spa://dom |
DOM structure |
Sử dụng với AI Agent
Cấu hình MCP
Thêm vào MCP config (ví dụ mcp_config.json):
{
"mcpServers": {
"web-viewer": {
"command": "node",
"args": ["<path-to-project>/out/mcp/mcp-server.js"]
}
}
}
Kiến trúc
AI Agent <--stdio--> MCP Server (node) <--HTTP:54321--> VS Code Extension <--postMessage--> Webview
Cấu trúc Project
├── media/ # Build output (Vite)
│ ├── index.html
│ ├── styles.css
│ └── bundle.js
├── src/
│ ├── extension.ts # Entry point + business logic
│ ├── core/ # Generic modules
│ │ ├── ViewerProvider.ts # Configurable webview
│ │ └── HttpBridge.ts # HTTP command router
│ ├── mcp/
│ │ └── mcp-server.ts # Standalone MCP server
│ ├── spa/
│ │ └── tools/
│ │ └── index.ts # Tool definitions
│ └── webview/ # Webview source (Vite)
│ ├── index.html
│ ├── styles.scss
│ ├── bridge.ts
│ └── main.ts
├── vite.config.ts
├── tsconfig.json
└── package.json
Customization
Thay đổi UI
Sửa files trong src/webview/, sau đó chạy npm run build:webview
Thêm MCP Tools
Sửa src/spa/tools/index.ts và src/mcp/mcp-server.ts
Thay đổi Config
Sửa src/extension.ts:
const webviewProvider = new WebviewProvider(context.extensionUri, {
viewType: 'your.viewType',
title: 'Your Title',
mediaFolder: 'media',
});
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.