MCP_AI_Monitor

🔍 Overview

MCP_AI_Monitor is a comprehensive system monitoring solution that uses unsupervised machine learning algorithms to detect abnormal behavior in resource usage. Designed to provide deep visibility into your system's performance in real time, it combines data collection, predictive analysis, and detailed reporting.

Related MCP server: Stealth-AntiCheat MCP

✨ Main Features

• 🤖 AI Anomaly Detection - Uses Isolation Forest to identify unusual system behaviors

• 📊 Real-time Analysis - Continuous monitoring of CPU, RAM and network metrics

• 🧠 Adaptive Learning - Adjusts to your system's normal behavior to reduce false positives

• 📱 Instant Notifications - System alerts when anomalies are detected

• 📈 Detailed Visualizations - Resource usage graphs with trend identification

• ⚙️ Process Analysis - Identification of resource-intensive applications

• 🌐 Network Monitoring - Analyze active connections and network performance

• 📡 Discord Integration - Detailed reports automatically sent to your Discord channels

• 🎨 Modern CLI Interface - Colorful and intuitive display in the terminal

🚀 Available orders

🛠️ Architecture

MCP_AI_Monitor is composed of several add-ons:

1. Data collection module ( collect_data.py )

   • Records system metrics at regular intervals

   • Stores data in CSV format for later analysis

2. AI Training Module ( train_model.py )

   • Pre-processes the collected data

   • Train an Isolation Forest model for anomaly detection

   • Save the model for real-time use

3. Monitoring module ( monitor_ai.py )

   • Uses the trained model to detect anomalies in real time

   • Implements a learning phase to adapt to normal behavior

   • Distinguishes application launches from real anomalies

4. Discord Integration

   • Sends separate reports for hardware and network

   • Uses configurable webhooks for each data category

   • Optimized visual format with thematic embeds

📊 Discord Reports

MCP_AI_Monitor generates detailed reports and sends them to Discord via dedicated webhooks:

Hardware reports

• System Information - Details about CPU, RAM, OS

• Usage Graphs - Visualize CPU/RAM Trends

• Active Processes - List of the most power-hungry applications

Network reports

• Network activity - Upload/download speeds, data volumes

• Network Interfaces - Details of active interfaces and their IP addresses

• Active Connections - Tracking established connections and associated processes

📋 Prerequisites

• Python 3.8+

• Python dependencies (installable via pip install -r requirements.txt ):

  • psutil - System Data Collection

  • scikit-learn - Machine learning algorithms

  • pandas - Data Manipulation

  • matplotlib - Graph generation

  • colorama - Colorful display in the terminal

  • discord-webhook - Integration with Discord

🔧 Installation

1. Clone this repository:

git clone https://github.com/MedusaSH/MCP_AI_Monitor.git
cd MCP_AI_Monitor

2. Install the dependencies:

pip install -r requirements.txt

3. Configure your Discord webhooks (optional):

   • Change the webhook URLs in the mcp.py file

   • Ability to use separate webhooks for hardware and network reports

📖 User guide

Quick Start

For a first full use:

# Collecte de données (60 secondes par défaut)
python mcp.py collect

# Entraînement du modèle IA
python mcp.py train

# Surveillance en temps réel
python mcp.py monitor

Automated workflow

To run the entire process in one command:

# Exécute la séquence complète et envoie un rapport sur Discord
python mcp.py all --duration 120 --report

🔍 Anomaly detection

The system uses an Isolation Forest algorithm to detect abnormal behavior:

1. Learning Phase - Collecting data to establish a baseline

2. Dynamic adaptation - Adjusting thresholds based on normal behavior

3. Smart Filtering - Detect app launches to reduce false positives

4. Anomaly Scoring - Classifying Events by Level of Abnormality

🌱 Contribution

Contributions are welcome! To contribute:

1. Fork the project

2. Create a branch for your feature ( 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

📜 License

This project is licensed under the MIT License. See the LICENSE file for more information.

👥 Authors

• MedusaSH - Initial Development - Github

🙏 Acknowledgments

• Forest insulation by scikit-learn

• psutil for accessing system metrics

• discord-webhook library for Discord integration