Skip to main content
Glama

๐Ÿ›ก๏ธ GhostWall - AI-Based Cyber Threat Detection Framework

React TypeScript Node.js Vite Express Vercel License: MIT

GhostWall is a full-stack, completely offline, AI-powered Cyber Threat Detection Framework. Designed with a premium, high-visibility security dashboard, GhostWall serves as a mock defensive operations console. It demonstrates how multi-agent security orchestrations (ADK) can scan network traffic, correlate audit logs, evaluate threat payloads, and trigger active firewall blocksโ€”entirely locally and without external API dependencies.

๐Ÿ”— Live Demo URL: https://ghostwall.vercel.app (Build ready for Vercel deployment)


๐Ÿ“Š Visual Walkthrough & Screenshots

๐Ÿ’ป System Security HUD

The main dashboard features glassmorphic control cards, a system health score index, real-time restricted IP counters, and throughput meters.

GhostWall Dashboard HUD

๐Ÿ“น Real-Time Agentic Response Simulation

Watch the local multi-agent system respond step-by-step to a volumetric DDoS attack and sanitize inputs in the payload scanner:

Real-Time Simulation Flow


Related MCP server: CrowdSentinel MCP Server

๐ŸŽฏ Key Features

  • ADK Multi-Agent System: Orchestrates specialized security agents working in a collaborative pipeline.

  • Model Context Protocol (MCP): Implements an offline JSON-RPC MCP structure to register resources and tools that agents can query and trigger.

  • Threat Simulator: Interactively trigger simulated attack vectors (DDoS, Brute Force, SQL Injection, XSS, Port Scans) and witness immediate real-time defensive reactions.

  • Payload Sanitizer Sandbox: An interactive playground demonstrating strict static sanitization methods (SQLi, XSS, Traversal, Command Injection) with zero risk of code execution.

  • CLI Utility Skills: Built-in script tools for directory log scanning and independent payload validation.

  • Modern Obsidian Styling: Sleek cyberpunk theme featuring glowing neon status indicators, interactive SVG icons, and a custom command-line log viewer.


๐Ÿ› ๏ธ Tech Stack

  • Frontend: React 18, Vite 5, Lucide Icons, Vanilla HSL CSS Variables (Obsidian glassmorphism design system)

  • Backend: Node.js, Express, Body Parser, CORS

  • Type Safety: TypeScript 5

  • Deployment: Vercel (integrated with Serverless Functions for full-stack compatibility)

  • Orchestration: ADK (Agent Development Kit) simulation engine


๐Ÿ—๏ธ System Architecture

GhostWall models a standard SOC (Security Operations Center) pipeline:

flowchart TD
    User([User Simulation Trigger]) -->|Select DDoS/SQLi/Brute Force| App[GhostWall Dashboard Client]
    App -->|POST /api/simulation/run| Express[Express.js Serverless Backend]
    
    subgraph Multi-Agent System [ADK Orchestration Engine]
        Express --> Manager[AgentManager]
        Manager -->|Step 1| NetAgent[Network Traffic Analyzer Agent]
        Manager -->|Step 2| LogAgent[Log Parser & Correlation Agent]
        Manager -->|Step 3| ThreatAgent[Threat Scoring Agent]
        Manager -->|Step 4| MitAgent[Response Mitigation Agent]
    end

    subgraph Local MCP Server [Model Context Protocol Server]
        NetAgent -->|Call Tool| Tool1[network_traffic_analyzer]
        LogAgent -->|Call Tool| Tool2[log_correlator]
        ThreatAgent -->|Call Tool| Tool3[payload_sanitize_validator]
        MitAgent -->|Call Tool| Tool4[firewall_mitigator]
        
        Manager -->|Read Resource| Resource1[ghostwall://threats/logs]
        Manager -->|Read Resource| Resource2[ghostwall://system/status]
    end

    Tool4 -->|Enforce Rule| Blacklist[(Firewall Blacklist / Memory Logs)]
    Blacklist -->|Report Status| App

๐Ÿค– Agent Directory & Roles

  1. Network Traffic Analyzer Agent: Scans connections for volumetric patterns (e.g. DDoS volume threshold anomalies).

  2. Log Parser & Correlation Agent: Links authentication failures with scanning events to spot multi-stage campaigns.

  3. Threat Classification & Scoring Agent: Inspects exploit payloads and assigns risk index scores (0-100).

  4. Automated Response Mitigation Agent: Determines containment actions (BLOCK_IP, RATE_LIMIT, ISOLATE_SUBNET).


๐Ÿ“‚ Project Directory Structure

โ”œโ”€โ”€ api/
โ”‚   โ””โ”€โ”€ index.ts                 # Vercel serverless entry point
โ”œโ”€โ”€ assets/
โ”‚   โ”œโ”€โ”€ initial_dashboard_view.png
โ”‚   โ””โ”€โ”€ ghostwall_threat_simulation_demo.webp
โ”œโ”€โ”€ server/
โ”‚   โ”œโ”€โ”€ index.ts                 # Express application & API routing
โ”‚   โ”œโ”€โ”€ mcp-server.ts            # Mock MCP JSON-RPC Server
โ”‚   โ”œโ”€โ”€ adk/
โ”‚   โ”‚   โ”œโ”€โ”€ agent-manager.ts     # Multi-agent orchestrator loop
โ”‚   โ”‚   โ”œโ”€โ”€ network-agent.ts     # Network security agent
โ”‚   โ”‚   โ”œโ”€โ”€ log-agent.ts         # Correlation agent
โ”‚   โ”‚   โ”œโ”€โ”€ threat-agent.ts      # Scoring agent
โ”‚   โ”‚   โ””โ”€โ”€ mitigation-agent.ts  # Firewall mitigation agent
โ”‚   โ””โ”€โ”€ scripts/
โ”‚       โ”œโ”€โ”€ log-collector.ts     # CLI Log Analyzer skill script
โ”‚       โ””โ”€โ”€ payload-validator.ts # Standalone static payload scanner
โ”œโ”€โ”€ src/
โ”‚   โ”œโ”€โ”€ App.tsx                  # Dashboard interface component
โ”‚   โ”œโ”€โ”€ main.tsx                 # React DOM bootstrapper
โ”‚   โ”œโ”€โ”€ index.css                # Obsidian cyber theme CSS styles
โ”‚   โ””โ”€โ”€ vite-env.d.ts            # Vite client type bindings
โ”œโ”€โ”€ index.html                   # HTML entry (Outfit & JetBrains Fonts)
โ”œโ”€โ”€ package.json                 # Project dependencies & build automation
โ”œโ”€โ”€ tsconfig.json                # TypeScript compilation config
โ”œโ”€โ”€ vercel.json                  # Vercel deployment rewrite routes
โ””โ”€โ”€ vite.config.ts               # Vite configuration with proxy settings

๐Ÿš€ Quick Setup & Installation

Prerequisites

  • Node.js (v18+)

  • npm (v9+)

Local Development

  1. Clone the repository and install dependencies:

    git clone https://github.com/anshikasingh28072006/GhostWall.git
    cd GhostWall
    npm install
  2. Run the full application locally:

    npm run dev

    This concurrent script launches the React client on http://localhost:3000 and proxy-binds to the Express backend API on http://localhost:3001.

CLI Security Tools

You can execute standalone tools directly in your terminal:

# Run log parser skill
npx ts-node server/scripts/log-collector.ts

# Run payload validator skill
npx ts-node server/scripts/payload-validator.ts "SELECT * FROM users WHERE 1=1"

โšก Vercel Deployment Instructions

GhostWall is deployed as a 100% client-side static React application. There is no backend server setup or API key configuration needed:

  1. Push Changes to GitHub: Ensure all local changes are committed and pushed to your repo.

  2. Import Project to Vercel:

    • Go to Vercel Dashboard and click Add New -> Project.

    • Import the GhostWall repository.

  3. Configure Settings:

    • Framework Preset: Vite

    • Root Directory: ./ (leave default)

    • Build Command: npm run build (runs tsc && vite build)

    • Output Directory: dist

  4. Deploy: Click Deploy. Vercel will build the React bundle and deploy the static site instantly.


๐Ÿ”ฎ Future Improvements

  • Add a live interactive threat map visualizing blocked geo-IP markers.

  • Implement exportable CSV reports for compliance auditing.

  • Expand signature lists to include SQLi-to-shell patterns.

  • Integrate WebSockets for live logging feeds.


๐Ÿ‘ฅ Author & Contact

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    An MCP server for offline network forensic analysis and threat intelligence, enabling LLMs to analyze PCAP files, extract streams, detect threats, and identify credentials using tshark.
    6
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables natural language threat hunting and incident response by connecting LLMs to enterprise security data sources like Elasticsearch, EVTX logs, PCAP files, and Velociraptor.
    38 PyPI
    206
    GPL 3.0
  • A
    license
    A
    quality
    D
    maintenance
    Dark web & threat intelligence for AI agents. HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis โ€” unified into a single MCP server.
    66
    158 npm
    457
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    Local, no-API-key MCP server with seven defensive SecOps tools for AI agents: extract IOCs (IPs, URLs, domains, hashes, CVE IDs) from text with defang/refang, hash strings, estimate password entropy, and run CIDR/subnet checks. Built on FastMCP with no outbound network calls.
    9
    MIT