React + Tailwind MCP Server Template
A full-stack template for building Model Context Protocol (MCP) servers with a modern React frontend, allowing developers to create AI agent tools and workflows while providing a beautiful web interface.
README
React + Tailwind MCP Server Template
A full-stack template for building Model Context Protocol (MCP) servers with a modern React frontend. This template provides a complete development environment where your MCP server not only exposes tools and workflows to AI agents but also serves a beautiful web interface built with React and Tailwind CSS.
✨ Features
- 🤖 MCP Server: Cloudflare Workers-based server with typed tools and workflows
- ⚛️ React Frontend: Modern React app with Vite, TanStack Router, and Tailwind CSS
- 🎨 UI Components: Pre-configured shadcn/ui components for rapid development
- 🔧 Type Safety: Full TypeScript support with auto-generated RPC client types
- 🚀 Hot Reload: Live development with automatic rebuilding for both frontend and backend
- ☁️ Ready to Deploy: One-command deployment to Cloudflare Workers
🚀 Quick Start
Prerequisites
- Node.js ≥18.0.0
- Deno ≥2.0.0
- Deco CLI:
deno install -Ar -g -n deco jsr:@deco/cli
Setup
# Install dependencies
npm install
# Configure your app
npm run configure
# Start development server
npm run dev
The server will start on http://localhost:8787 serving both your MCP endpoints
and the React frontend.
📁 Project Structure
├── server/ # MCP Server (Cloudflare Workers + Deco runtime)
│ ├── main.ts # Server entry point with tools & workflows
│ └── deco.gen.ts # Auto-generated integration types
└── view/ # React Frontend (Vite + Tailwind CSS)
├── src/
│ ├── lib/rpc.ts # Typed RPC client for server communication
│ ├── routes/ # TanStack Router routes
│ └── components/ # UI components with Tailwind CSS
└── package.json
🛠️ Development Workflow
npm run dev- Start development with hot reloadnpm run gen- Generate types for external integrationsnpm run gen:self- Generate types for your own tools/workflowsnpm run deploy- Deploy to production
🔗 Frontend ↔ Server Communication
The template includes a fully-typed RPC client that connects your React frontend to your MCP server:
// Typed calls to your server tools and workflows
const result = await client.tools.MY_TOOL({ input: "data" });
const workflowResult = await client.workflows.MY_WORKFLOW({ input: "data" });
📖 Learn More
This template is built for deploying primarily on top of the Deco platform which can be found at the deco-cx/chat repository.
Ready to build your next MCP server with a beautiful frontend? Get started now!
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。