{"id":"8eafac12-3108-4120-9a78-2e895de9a947","slug":"threat-detection-system","kind":"mcp","name":"Threat-Detection-System","summary":"The application uses C++ for file system monitoring, machine learning for behavior analysis and logging, and RS256 encryption for data security, while Agentic AI develops detection algorithms, transla","owner":"ben854719","repoUrl":"https://github.com/ben854719/Threat-Detection-System","license":"MIT","licenseTier":"permissive","trust":"community","stars":0,"match":null,"fewStars":true,"format":"mcp","createdAt":"2025-08-29T18:18:09.000Z","addedAt":"2026-10-21T04:05:02.466Z","logoUrl":"https://avatars.githubusercontent.com/u/185095765?u=2013a5928ed9195b165559f0d18f3daf1b2b74bb&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["cloud-infra","files-documents","data-analytics"],"tags":["agentic-ai","cybersecurity","gemini","langgraph","python","rs256","software","translation"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-24T04:08:07.003Z","sample":false,"url":"https://conduits.dev/tools/threat-detection-system","language":"Jupyter Notebook","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Threat-Detection-System\n\n## Objective:\n\nThe application delivers a smart threat detection system for the client business by using C++ to monitor the file system changes in real time, by processing over 50,000 events per minute with minimal CPU usage. The suspicious activity is log locally or sent to a Python engine via named pipes, enabling efficient communication under 10ms latency. Python applies machine learning trained on 15,000+ threat events, achieving 96.3% accuracy and under 3.1% false positives. The RS256 asymmetric encryption secures the data of the client business. The Agentic AI generates adaptive detection algorithms and translates reports from English to French with 99.8% accuracy, enabling the cybersecurity team to isolate the attacks in real time and reduce the ransomware spread by 89% within 60 seconds of the client business.\n\n# Video of the Project:\n\nhttps://github.com/user-attachments/assets/84737a52-8a3f-4b7d-83b5-adfb8b72c929\n\n# Key Features:\n\n## Real-Time File System Monitoring:\n\n- C++ agent tracks over 50,000 file events per minute with less than 2% CPU usage, ensuring lightweight performance across client machines.\n\n## Secure Inter-Process Communication:\n\n- Named pipes transmit suspicious activity from C++ to Python with latency under 10 milliseconds, maintaining fast and secure data flow.\n\n## High-Accuracy Anomaly Detection:\n\n- Python ML engine trained on 15,000+ threat events, achieving 96.3% detection accuracy and a false positive rate below 3.1%.\n\n## Enterprise-Grade Encryption:\n\n- RS256 asymmetric encryption use to secure and protect the confidential data of the client business, ensuring integrity and confidentiality through robust public-key cryptography.\n\n## Agentic AI Intelligence:\n\n- Generates adaptive detection algorithms and translates reports from English to French with 99.8% linguistic accuracy, supporting bilingual security teams.\n\n## Automated Cybersecurity Response:\n\n- Real-time alerts and isolation protocols reduce ransomware spread by 89% within the first 60 seconds, minimizing damage and downtime.\n\n# Installation:\n\n## Prerequistes:\n\n- Python\n- C++\n- Machine Learning Algorithm\n- Crytography\n- RS256 Assymetric Encryption\n- Sklearn\n- RainforestClassifer\n- Named Pipe Server\n- Joblib\n- Agentic AI\n- LanGraph\n- Gemini\n- MCP Server\n\n# Agentic AI Configuration (with MCP Server Installation):\n\n## API Credentials:\n\n- Register and obtain your Gemini API key from Google AI Studio.\n- Store the key securely in a .env file to protect sensitive credentials.\n  \n## LangGraph Flow Setup:\n\n- Design a multi-step processing graph to handle translation and reporting.\n- Node Configuration.\n- Input Normalization – Preprocess incoming text for consistency and clarity.\n- Gemini Translation Output – Use Gemini API to translate English threat reports to French.\n- Language Detection – Automatically identify the source language for routing and fallback handling.\n\n## Integrate with MCP Server:\n\n## Ensure MCP can:\n\n- Receive incoming reports\n- Trigger LangGraph flow\n- Store or forward translated output\n\n## Run the Flow:\n\n- Normalize → Detect → Translate (if English) → Fallback (if needed) → Output\n\n\n\n\n\n"}