MCP Client

By swairshah GitHub

Overview

What is MCP Client?

MCP Client is an interactive AI assistant interface that features a dual-display system, combining a terminal-based command-line interface (CLI) with an always-on-top window for real-time monitoring of model outputs.

How to use MCP Client?

To use MCP Client, clone the repository, install the necessary dependencies, and start the application. You can interact with the AI through the terminal while monitoring outputs in the floating window.

Key features of MCP Client?

Terminal Interface for command input
Always-on-top display for real-time output monitoring
Pause functionality to halt model execution
User input requests during long-running tasks
Global shortcuts for easy access to features
Integration with Model Context Protocol (MCP) servers

Use cases of MCP Client?

Control your computer with AI assistance.
Automate browser interactions while monitoring AI actions.
Manage long-running tasks with real-time feedback.
Ensure safety by observing AI actions as they occur.

FAQ from MCP Client?

What are the prerequisites for using MCP Client?

You need Node.js (v12 or higher), npm, Python 3.7+, and the MCP library for server integration.

How do I install MCP Client?

Clone the repository, install dependencies using npm and pip, and start the application with Python.

Can I customize the MCP server settings?

Yes! You can configure your MCP server in the backend/server.config file.

Content

MCP Client

An interactive AI assistant interface with a dual-display system: a terminal-based CLI for commands and an always-on-top window for real-time model output monitoring.

Features

Terminal Interface: Interact with the AI assistant through a command-line interface
Always-on-top Display Window: Monitor model outputs in real-time
- Translucent window with modern design
- Stays on top of other applications
- Follows you across virtual desktops
Real-time Output Monitoring: See what the model is generating as it happens
Pause Functionality: Pause model execution if you see undesired actions being generated
User Input Requests: The display window can request user input while long-running tasks continue in the CLI
Global Shortcuts:
- Ctrl/Cmd + Shift + T to toggle the follow desktop behavior
- Ctrl/Cmd + Shift + P to pause/resume model execution
MCP Integration: Connect to Model Context Protocol (MCP) servers for enhanced AI capabilities

Use Cases (all of them TODO...)

Computer Control: Use the MCP client to control your computer with AI assistance
Browser Automation: Navigate and interact with web browsers while monitoring AI actions
Long-running Tasks: Monitor progress and provide input while background tasks run
Safety Monitoring: Observe and control AI actions in real-time

Getting Started

Prerequisites

Node.js (v12 or higher)
npm
Python 3.7+
MCP library (for MCP server integration)

Installation

Clone this repository

Install dependencies:

npm install
pip install -r backend/requirements.txt
pip install mcp

Start the application:
```
python backend/cli.py
```

Usage

The application runs in two parts:

Terminal Interface: Where you input commands and see primary responses
Floating Window: Where you can monitor model outputs in real-time

Terminal Commands

The CLI supports various commands for interacting with the AI assistant. Type help in the terminal for a list of available commands.

Display Window Controls

Pause Button: Click to pause model execution if you see undesired actions
Toggle Follow Desktop: Enable/disable the window following you across virtual desktops
Drag: Click and drag anywhere on the window to reposition it

MCP Server Integration

The application can connect to MCP servers for enhanced AI capabilities:

Configure your MCP server in backend/server.config:

{
  "llm_type": "mcp",
  "server_path": "/path/to/your/mcp_server.py",
  "server_name": "your-mcp-server",
  "server_version": "0.1.0"
}

Install the MCP library:
```
pip install mcp
```
Start the application with MCP integration:
```
python backend/cli.py
```

The application will automatically connect to the specified MCP server and use it for generating responses. If the MCP server is not available, it will fall back to the mock LLM implementation.

Architecture

The application consists of:

Electron frontend for the always-on-top display window
Python backend with Flask API for handling AI interactions
Terminal-based CLI for user input and command processing

License

ISC

No tools information available.

No content found.