mcp-frontend

MCP.Pizza Chef: shaharia-lab

mcp-frontend is a React and TypeScript-based client application for the Model Context Protocol (MCP) Kit. It provides a modern, responsive single-page interface enabling real-time chat with large language models (LLMs) and tool-based interactions. Designed to integrate seamlessly with MCP backend servers, it facilitates enhanced LLM workflows through a user-friendly web UI.

Use This MCP client To

Engage in real-time chat with LLMs using MCP protocol Interact with MCP backend servers via a responsive web UI Leverage tool-based capabilities in LLM conversations Build custom AI-powered web applications with MCP integration Test and demo MCP Kit features in a browser environment

README

MCP (Model Context Protocol) Frontend

License: MIT

A frontend application for the Model Context Protocol (MCP) Kit that enables enhanced interactions with Large Language Models through tool-based capabilities.

This repository is part of mcp-kit and serves as the user interface layer built with modern web technologies.

πŸš€ Features

  • Single Page Application architecture
  • Real-time chat interface with LLMs
  • Tool-based interaction capabilities
  • Integration with MCP backend server
  • Modern, responsive UI built with React and TypeScript

πŸŽ₯ Demo

Experience MCP Kit in action - chat with LLMs while leveraging additional capabilities provided by the MCP server:

mcp-frontend-demo.mp4

πŸ› οΈ Prerequisites

  • Node.js 20.x
  • NPM 7.x

πŸ“¦ Installation

Standard Installation

  1. Clone the repository:
git clone https://github.com/shaharia-lab/mcp-frontend.git
cd mcp-frontend

[Rest of standard installation steps...]

🐳 Docker Installation

You can run MCP Frontend using our official Docker image:

docker pull ghcr.io/shaharia-lab/mcp-frontend:<version>

Replace <version> with the specific version you want to use (e.g., latest, 1.0.0).

Running with Docker

docker run
-p 3000:3000
-e VITE_MCP_BACKEND_API_ENDPOINT=http://localhost:8081
ghcr.io/shaharia-lab/mcp-frontend:

Environment Variables

The following environment variables are required to run MCP Frontend:

env_key Default Required Description
VITE_MCP_BACKEND_API_ENDPOINT - Yes The base URL for the MCP backend API.

Simply copy the .env.example file to .env and update the values as needed to run the application locally. And for Docker, you can pass the environment variables using the -e flag.

πŸš€ Usage

Development

Run the development server:

npm run dev

Production

Build for production:

npm run build

For detailed configuration options, refer to the Vite documentation.

πŸ—οΈ Architecture

MCP Frontend is built with:

🀝 Contributing

We welcome contributions! Here's how you can help:

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Please ensure your PRs follow our coding standards and include appropriate tests.

πŸ” Related Projects

⚠️ Current Status

This project is under active development. While functional, it's not yet recommended for production use. We're working on:

  • Enhanced error handling
  • Improved performance
  • Additional tool integrations
  • Comprehensive testing suite

πŸ“ License

This project is licensed under the MIT License - see the LICENSE file for details.

πŸ€” Support

πŸ™ Acknowledgments

  • The MCP Kit community
  • All our contributors and supporters

mcp-frontend FAQ

What technologies is mcp-frontend built with?
It is built using React and TypeScript for a modern web experience.
How does mcp-frontend connect to MCP backend servers?
It integrates via the MCP protocol to enable real-time data exchange and tool interactions.
What prerequisites are needed to run mcp-frontend?
Node.js 20.x and NPM 7.x or higher are required to install and run the frontend.
Can mcp-frontend be customized for different MCP workflows?
Yes, its modular React architecture allows customization for various MCP-based applications.
Does mcp-frontend support multiple LLM providers?
Yes, it supports OpenAI, Anthropic Claude, and Google Gemini through MCP integration.
Is mcp-frontend suitable for production use?
It is designed as a ready-to-use frontend and can be adapted for production environments.
How does mcp-frontend handle tool-based interactions?
It provides UI components to invoke and manage MCP tools during LLM conversations.
Where can I find a demo of mcp-frontend?
A demo video is available in the GitHub repository showcasing its real-time chat and tool features.