About MCP Chat Demo
MCP Chat Demo is a sample chat application showing how to connect with MCP servers, built with React and TypeScript. It connects to local or remote servers and supports using their tools and resources in chat.
Key features
- 01Connect to local or remote MCP servers
- 02Real-time chat interface
- 03MCP tools and resources support
- 04Message history
- 05Error handling and reconnection
Use cases
- 01Demonstrating MCP server integration in a chat app
- 02Using MCP tools and resources in chat
MCP support
The application connects to local or remote MCP servers and uses their tools and resources through its chat interface.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Chat Demo
A sample chat application demonstrating integration with Model Context Protocol (MCP) servers.
Project Structure
mcp-chat-demo/
├── package.json
├── README.md
├── .gitignore
├── src/
│ ├── App.tsx
│ ├── main.tsx
│ ├── components/
│ │ ├── Chat.tsx
│ │ ├── MessageList.tsx
│ │ ├── MessageInput.tsx
│ │ └── MCPConnection.tsx
│ ├── lib/
│ │ ├── mcp-client.ts
│ │ └── types.ts
│ └── styles/
│ └── main.css
└── public/
└── index.html
Setup Instructions
- Clone the repository:
git clone https://github.com/yourusername/mcp-chat-demo.git
cd mcp-chat-demo
- Install dependencies:
npm install
- Start the development server:
npm run dev
Features
- Connect to local or remote MCP servers
- Real-time chat interface
- Support for MCP tools and resources
- Message history
- Error handling and reconnection logic
Technology Stack
- React 18
- TypeScript
- Vite
- TailwindCSS
- MCP TypeScript SDK
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.