MCP Sigmund

🚀 MCP Sigmund

A Model Context Protocol (MCP) server for financial data analysis and learning, leveraging a unified PostgreSQL database as the primary data source. It features intelligent formatting with progressive disclosure for an optimal user experience.

🚀 Quick Start

After installation, you can start using MCP Sigmund with these basic queries:

• "Show me my balance" - Get current account balances
• "List my recent transactions" - View recent transaction history
• "Analyze my spending" - Get spending analysis by category
• "What providers do I have?" - List connected banking providers

For detailed usage instructions, examples, and advanced features, see the User Guide.

✨ Features

• 🗄️ Database-Driven - Uses PostgreSQL database as primary data source with normalized banking data
• 🏦 Multi-Provider Support - Unified data from multiple Open Banking sources (banks and aggregators)
• 🎯 Smart Formatting - Intelligent defaults with progressive disclosure for optimal UX
• 🔄 Context Detection - Automatically adapts formatting based on user intent
• 🌐 ALL Providers Default - When no provider is specified, queries ALL providers by default
• 🛡️ Comprehensive Error Handling - Robust validation and error management
• ✅ Full Test Coverage - Unit and integration tests for reliability
• 📝 TypeScript Support - Type-safe development with comprehensive type definitions
• 🔐 Secure Configuration - Centralized auth system with credential protection
• 🔒 Security Features - Password sanitization, input validation, and secure logging
• 📊 Structured Logging - Comprehensive logging with context and error tracking
• ⚡ Performance Monitoring - Query performance tracking and health monitoring

📦 Installation

Prerequisites

• Node.js (v18 or later)
• PostgreSQL database with financial data
• npm or yarn
• TypeScript knowledge

Steps

1. Clone this repository:

git clone <repository-url>
cd mcp-sigmund

2. Install dependencies:

npm install

3. Set up the database:

   Option A: Import from Database Dump (Recommended)

   # Create the database
   createdb mcp-sigmund
   
   # Import the provided database dump
   psql -d mcp-sigmund -f mcp-sigmund-dump.sql
   

   Option B: Use Existing Database

   • Ensure your PostgreSQL database contains the required schema (see Database Documentation)
   • Update the connection string in the configuration

4. Configure database connection:

   • Copy src/auth.example.ts to src/auth.ts
   • Update the PostgreSQL connection string in src/auth.ts:

     connectionString: "postgresql://username:password@host:port/database"
     

   • Adjust connection pool settings if needed

5. Build the project:

npm run build

6. Run tests to verify everything works:

npm test

📚 Documentation

• User Guide - Complete user guide with configuration, tools, and examples
• Development Guide - Developer documentation, testing, and contribution guidelines
• Database Documentation - Database setup, schema, and import instructions
• Roadmap - Future development plans and feature roadmap
• Next Steps - Immediate action items and implementation details

⚠️ Important Note

⚠️ Important Note

MCP Sigmund is an educational learning resource and data analysis tool, NOT a financial advisor or advisory service.

🚫 NOT FINANCIAL ADVICE

• This system does NOT provide financial advice, recommendations, or guidance
• All insights, analysis, and suggestions are for educational purposes only
• Users must make their own financial decisions based on their own research and judgment
• No information from this system should be considered as investment, tax, or financial advice

📚 Educational Purpose Only

• MCP Sigmund is designed as a learning resource for understanding personal financial data
• The system helps users analyze and understand their financial patterns and trends
• All outputs are intended for educational and informational purposes
• Users should consult qualified financial professionals for actual financial advice

By using MCP Sigmund, you acknowledge this is an educational tool, not a financial advisory service.

Overview

MCP Sigmund enables AI assistants (like Claude) to interact with financial data through the Model Context Protocol. Unlike API-based solutions, this server uses a pre-populated PostgreSQL database containing financial data imported from Open Banking sources (directly from banks like Deutsche Bank or via account aggregators like TrueLayer and Tink), with smart formatting that adapts to user context automatically.

📄 License

ISC License - see LICENSE file for details

Disclaimer

This project is for educational and development purposes. Use at your own risk and ensure compliance with relevant financial regulations and data privacy requirements.