Happy slice of mcp pizzaMCP.pizza

chat-mcp

MCP.Pizza Chef: AI-QL

Built with Electron for Windows, macOS and Linux, it is a deliberately bare chat window whose whole point is showing how the protocol fits together: you aim it at any chat model that speaks the common OpenAI format, add the tool servers you want, and start talking. The same author has since rebuilt it as TUUI, a tidier and far busier desktop app, and this original has had no code changes since September 2025. You bring your own model key and run it from source.

Deprecated · rebuilt as TUUI, which the author points people to
Coding
Other

Use This MCP client To

Try out a new MCP tool without touching my main assistant Chat with several different models from one window See exactly what a tool sends back while I test it Read simple code to understand how MCP actually works Start my own desktop chat app from a small example

README

MCP Chat Desktop App

A Cross-Platform Interface for LLMs

This desktop application utilizes the MCP (Model Context Protocol) to seamlessly connect and interact with various Large Language Models (LLMs). Built on Electron, the app ensures full cross-platform compatibility, enabling smooth operation across different operating systems.

The primary objective of this project is to deliver a clean, minimalistic codebase that simplifies understanding the core principles of MCP. Additionally, it provides a quick and efficient way to test multiple servers and LLMs, making it an ideal tool for developers and researchers alike.

News

This project originated as a modified version of Chat-UI, initially adopting a minimalist code approach to implement core MCP functionality for educational purposes.

Through iterative updates to MCP, I received community feedback advocating for a completely new architecture - one that eliminates third-party CDN dependencies and establishes clearer modular structure to better support derivative development and debugging workflows.

This led to the creation of Tool Unitary User Interface, a restructured desktop application optimized for AI-powered development. Building upon the original foundation, TUUI serves as a practical AI-assisted development paradigm, if you're interested, you can also leverage AI to develop new features for TUUI. The platform employs a strict linting and formatting system to ensure AI-generated code adheres to coding standards.

📢 Update: June 2025
The current project refactoring has been largely completed, and a pre-release version is now available. Please refer to the following documentation for details:

Features

  • Cross-Platform Compatibility: Supports Linux, macOS, and Windows.

  • Flexible Apache-2.0 License: Allows easy modification and building of your own desktop applications.

  • Dynamic LLM Configuration: Compatible with all OpenAI SDK-supported LLMs, enabling quick testing of multiple backends through manual or preset configurations.

  • Multi-Client Management: Configure and manage multiple clients to connect to multiple servers using MCP config.

  • UI Adaptability: The UI can be directly extracted for web use, ensuring consistent ecosystem and interaction logic across web and desktop versions.

Architecture

Adopted a straightforward architecture consistent with the MCP documentation to facilitate a clear understanding of MCP principles by:

DeepWiki

chat-mcp FAQ

Is this still being worked on?
Not meaningfully. The author rebuilt it from scratch as TUUI and points people there; this repository's last code change was September 2025. It still runs, but new work happens elsewhere.
Should I use this or TUUI?
TUUI, unless you specifically want the smallest possible example to read and learn from. That is the one advantage this version keeps.
Do I need a key?
Yes. It has no model of its own, so you supply a key for a service that follows the common OpenAI format. The notes show settings for OpenAI, Qwen and DeepInfra.
How do I install it?
There is no ready-made download. You copy the code, install Node.js, then run two commands to fetch its parts and launch it, or build your own app package.
Can I use this to test a tool server before adding it to my main assistant?
Yes, and that is largely what it exists for. It comes set up with a few sample servers, including one for reading files and one for driving a web browser.
Which tool servers does it work with?
Any of them, in principle. Servers are listed in a settings file exactly as they would be in other MCP apps, so anything that works elsewhere should work here.