🍯 Honeypot Transaction Monitoring System
About
Enterprise-grade MCP server providing real-time transaction monitoring and fraud detection capabilities for honeypot virtual credit cards with Lithic.com. Features instant SSE alerts, comprehensive transaction intelligence, and sophisticated merchant analysis for advanced scammer
Details
- Author
- Thinh-nguyen-03
- Downloads
- 301
- Categories
- Developer Tools
Jump to
- Real‑time transaction alerts via Server‑Sent Events
- Virtual card creation and management through Lithic API
- Merchant analysis with MCC categorization and pattern recognition
- Comprehensive transaction intelligence and risk assessment metrics
- Enterprise‑grade validation, structured logging, and health monitoring
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
🍯 Honeypot Transaction Monitoring SystemCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, run npm install, configure environment variables (Supabase URL, Lithic API key, etc.), ensure the required Supabase database tables exist, then start the server with npm run dev or npm start. AI agents can connect to the SSE alert stream at /api/alerts/stream/:cardToken using an Authorization Bearer token.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83c\udf6f honeypot transaction monitoring system": {
"honeypot-mcp-server": {
"command": "node",
"args": [
"tests/unit/services/alert-service.test.js"
]
}
}
}
}
McpServers
{
"honeypot-mcp-server": {
"command": "node",
"args": [
"tests/unit/services/alert-service.test.js"
]
}
}
🍯 Honeypot Transaction Monitoring System
> Enterprise-grade fraud detection platform with real-time AI integration for advanced scammer verification and transaction monitoring.
🎯 Overview
The Honeypot Transaction Monitoring System is a sophisticated fraud detection platform that leverages Lithic virtual cards as honeypots to detect and analyze fraudulent activities in real-time. The system integrates with AI agents to enable dynamic scammer verification during live conversations, providing comprehensive transaction intelligence for effective fraud prevention.
Key Value Propositions
- 🚨 Real-Time Fraud Detection: Sub-second transaction alerts to AI agents during live scammer interactions
- 🧠 Advanced Transaction Intelligence: Comprehensive merchant analysis, pattern recognition, and verification data
- 🔒 Enterprise Security: Bank-grade security with comprehensive validation and error handling
- ⚡ High Performance: Optimized for high-frequency transaction processing with <100ms response times
- 🔗 Seamless Integration: REST APIs and Server-Sent Events for easy AI agent integration
---
🚀 Features
✅ Implemented (v1.0)
Core Transaction Processing
- Virtual card creation and management via Lithic API - Real-time transaction webhook processing - Comprehensive merchant data matching and categorization - MCC (Merchant Category Code) analysis and caching - Transaction pattern analysis and intelligenceReal-Time Alert System
- Server-Sent Events (SSE) for instant transaction notifications - Connection Management with health monitoring and auto-recovery - Multi-Agent Support with concurrent AI agent connections - Intelligent Alert Formatting with scammer verification data points - Enterprise Error Handling with graceful degradationData Intelligence
- Advanced transaction parsing and normalization - Merchant verification and categorization - Geographic pattern analysis - Transaction history and trend analysis - Real-time risk assessment metricsEnterprise Infrastructure
- Comprehensive Validation with Joi-based request sanitization - Structured Logging with Pino for production monitoring - Health Monitoring with detailed system metrics - Extensive Testing with 40+ unit and integration tests - Background Processing with automated transaction polling🔄 In Development
Enhanced Vapi Integration (Tasks 4.1-4.4)
- Advanced MCP (Model Context Protocol) server implementation - Real-time alert subscription management for AI agents - Transaction data query API with historical analysis - Enhanced conversation context integrationSystem Integration (Tasks 5.1-5.3)
- Complete route integration and middleware configuration - Advanced health monitoring and performance metrics - Production-ready deployment configuration---
🛠 Technology Stack
Backend Infrastructure
- Runtime: Node.js 18+ with ES Modules - Framework: Express.js 4.18+ with enterprise middleware - Database: Supabase (PostgreSQL) with real-time capabilities - External APIs: Lithic Financial API for virtual cardsReal-Time & Communication
- Alert Delivery: Server-Sent Events (SSE) - Connection Management: Custom connection pooling and health monitoring - AI Integration: Vapi with Model Context Protocol (MCP)Security & Validation
- Request Validation: Joi with comprehensive schema validation - Error Handling: Enterprise-grade error isolation and recovery - Logging: Structured logging with Pino for production monitoringDevelopment & Quality
- Testing: Comprehensive unit, integration, and E2E test suites - Code Quality: ESLint, Prettier, and enterprise coding standards - Monitoring: Built-in health checks and performance metrics---
📋 Prerequisites
- Node.js 18.0.0 or higher
- npm 9.0.0 or higher
- Supabase account and project
- Lithic API account and credentials
- Git for version control
---
⚡ Quick Start
1. Clone and Install
git clone https://github.com/your-org/honeypot-transaction-monitoring-system.git
cd honeypot-transaction-monitoring-system
npm install
2. Environment Configuration
Create a .env file in the root directory:
```env
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





