@deepbim/chatbot-mcp
v0.1.0
Published
A powerful, embeddable AI chatbot component with Model Context Protocol (MCP) support for React and Next.js applications.
Readme
Chatbot MCP
A powerful, embeddable AI chatbot component with Model Context Protocol (MCP) support for React and Next.js applications.
Features
- 🤖 AI-Powered Chat Interface - Built with Vercel AI SDK for seamless AI interactions
- 🔌 MCP Integration - Full support for Model Context Protocol servers
- 🎨 Customizable UI - Beautiful, responsive design with Tailwind CSS
- 💬 Thread Management - Persistent conversation threads with local storage
- 🛠️ Tool Selection - Dynamic MCP tool discovery and selection
- 📁 File Attachments - Support for uploading and processing files
- 🎯 Drag & Resize - Flexible positioning and sizing for optimal UX
- 🌐 Multi-Model Support - Works with various AI models (OpenAI, Anthropic, etc.)
- ⚡ TypeScript - Fully typed for better developer experience
Installation
npm install @24ktwin-editor/chatbot-mcp
# or
pnpm add @24ktwin-editor/chatbot-mcpPeer Dependencies
Make sure you have the following peer dependencies installed:
npm install react react-domUsage
Basic Integration
import { Chatbot } from '@24ktwin-editor/chatbot-mcp';
function App() {
return (
<div>
<Chatbot />
</div>
);
}Next.js App Router
// app/layout.tsx
import { Chatbot } from '@24ktwin-editor/chatbot-mcp';
export default function RootLayout({
children,
}: {
children: React.ReactNode;
}) {
return (
<html lang="en">
<body>
{children}
<Chatbot />
</body>
</html>
);
}Configuration
The chatbot will automatically check for your backend API at startup. Make sure your API endpoints are configured correctly:
- Health Check:
/api/v1/health - Chat API:
/api/v1/chat
Development
Prerequisites
- Node.js 18+
- pnpm (recommended) or npm
Setup
# Clone the repository
git clone <repository-url>
cd chatbot-mcp-nextjs
# Install dependencies
pnpm install
# Run development server
pnpm devOpen http://localhost:3000 to see the demo application.
Building
Build Next.js App
pnpm build
pnpm startBuild as NPM Package
pnpm build:libThis generates:
dist/index.mjs- ES Module formatdist/index.cjs- CommonJS formatdist/index.d.ts- TypeScript type definitions
Publishing
pnpm publish --access publicArchitecture
The chatbot is built with modular components:
- Chatbot Container - Main chat interface with message display
- Message Bubble - Individual message rendering with entity support
- Prompt Input - User input with file attachment support
- Settings Dialog - AI model and parameter configuration
- MCP Dashboard - MCP server management and tool selection
- Chat Sidebar - Thread history and management
Tech Stack
- Framework: Next.js 16 with App Router
- UI Library: React 19
- AI SDK: Vercel AI SDK (@ai-sdk/react)
- Styling: Tailwind CSS 4
- UI Components: Radix UI
- Animations: Framer Motion
- Build Tool: Rollup (for library builds)
- Language: TypeScript
API Requirements
Your backend should implement the following endpoints:
Health Check
GET /api/v1/health
Response: { status: "ok" }Chat API
POST /api/v1/chat
Content-Type: application/json
{
"threadId": "string",
"messages": [...],
"modelConfig": {...}
}Browser Support
- Chrome (latest)
- Firefox (latest)
- Safari (latest)
- Edge (latest)
License
MIT License - See LICENSE.md for details.
Copyright (c) 2026 SJ Group
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues and questions, please open an issue on GitHub.
