Statistics MCP Server

A Model Context Protocol (MCP) server that provides statistical analysis tools for sales and salary data. This server exposes business intelligence functions that can be used by AI assistants and other MCP-compatible clients.

🚀 Features

• Sales Analytics: Calculate total sales, find popular products, and analyze order patterns

• Product Intelligence: Identify most ordered products and highest value orders

• Salary Statistics: Compute salary metrics including averages, min/max values

• MCP Compatible: Works with Claude Desktop and other MCP clients

• TypeScript: Full type safety and modern development experience

• NestJS Framework: Built with enterprise-grade Node.js framework

Related MCP server: MCP Data Wrangler

📊 Available Tools

🏗️ Project Structure

mcp-server/
├── src/
│   ├── statistics/
│   │   ├── statistics.service.ts    # Business logic and data operations
│   │   ├── statistics.controller.ts # REST API endpoints (NestJS)
│   │   ├── statistics.module.ts     # NestJS module configuration
│   │   └── statistics.types.ts      # TypeScript interfaces
│   ├── mcp/
│   │   └── mcp-server.ts           # MCP server implementation
│   ├── mcp-main.ts                 # MCP server entry point
│   ├── main.ts                     # NestJS application entry point
│   └── app.*                       # NestJS app configuration
├── test/                           # E2E tests
├── dist/                          # Compiled JavaScript output
├── mcp-config.json                # MCP client configuration
├── package.json                   # Dependencies and scripts
└── README.md                      # This file

🛠️ Technology Stack

• Runtime: Node.js

• Language: TypeScript

• Framework: NestJS

• Protocol: Model Context Protocol (MCP)

• Testing: Jest

• Linting: ESLint

📋 Prerequisites

• Node.js (v18 or higher)

• npm or yarn package manager

⚡ Quick Start

1. Install Dependencies

npm install

2. Build the Project

npm run build

3. Start MCP Server

npm run start:mcp
# or directly:
node dist/mcp-main.js

4. Start NestJS Server (Alternative)

npm run start
# Development mode:
npm run start:dev

🔧 Configuration

MCP Client Configuration

Add this configuration to your MCP client (e.g., Claude Desktop):

{
  "mcpServers": {
    "statistics-server": {
      "command": "node",
      "args": ["/home/mamun/official/mcp-server/dist/mcp-main.js"],
      "env": {}
    }
  }
}

For Claude Desktop

Add to ~/.config/claude-desktop/claude_desktop_config.json (Linux):

{
  "mcpServers": {
    "statistics-server": {
      "command": "node",
      "args": ["/home/mamun/official/mcp-server/dist/mcp-main.js"],
      "env": {}
    }
  }
}

🧪 Testing

Run Unit Tests

npm run test

Run E2E Tests

npm run test:e2e

Test with MCP Inspector

npx @modelcontextprotocol/inspector dist/mcp-main.js

📡 API Endpoints (NestJS)

The server also provides REST API endpoints:

Example API Usage

# Start the NestJS server
npm run start

# Make API requests
curl http://localhost:3000/statistics/total-sales
curl http://localhost:3000/statistics/popular-product

🔄 MCP Protocol Flow

1. AI Client connects to MCP server
2. Client requests available tools
3. Server responds with tool definitions
4. Client calls a specific tool (e.g., "get_total_sales")
5. Server executes the corresponding service method
6. Server returns structured result
7. AI uses the result in its response to user

📊 Sample Data

The server includes sample data for demonstration:

Products

• Laptop ($999.99)

• Mouse ($24.99)

• Keyboard ($79.99)

• Monitor ($299.99)

• Headphones ($149.99)

Orders

• Multiple orders with different products and quantities

• Total sales calculation across all orders

Salaries

• Sample employee salary data for statistical analysis

🚀 Development

Development Mode

npm run start:dev

Build for Production

npm run build
npm run start:prod

Linting

npm run lint
npm run lint:fix

🔧 Available Scripts

🏆 Best Practices Implemented

1. Separation of Concerns: Business logic in services, MCP logic in dedicated server

2. Type Safety: Full TypeScript implementation with proper interfaces

3. Error Handling: Comprehensive error handling in MCP tools

4. Validation: Input validation for all operations

5. Documentation: Clear documentation and examples

6. Testing: Unit and E2E test setup

7. Code Quality: ESLint configuration for consistent code style

🤝 Contributing

1. Fork the repository

2. Create a feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add 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.

📞 Support

For questions and support:

• Create an issue in the repository

• Check the MCP Documentation

• Review the NestJS Documentation

🎯 What You've Learned

By studying this project, you now understand:

• ✅ MCP Basics: What MCP is and how it works

• ✅ Server Architecture: How to structure an MCP server project

• ✅ Tool Implementation: How to expose business logic as MCP tools

• ✅ Client Integration: How AI clients connect and use your tools

• ✅ TypeScript Development: Modern TypeScript with NestJS

• ✅ Testing: How to test MCP servers

• ✅ Deployment: How to build and deploy MCP servers

🚀 Next Steps

1. Add Authentication: Implement security for your MCP server

2. Database Integration: Connect to real databases instead of sample data

3. More Tools: Add additional statistical analysis tools

4. Resources: Implement MCP resources for file/data access

5. Prompts: Add MCP prompts for AI interaction templates

6. Production Deployment: Deploy to cloud platforms

7. Monitoring: Add logging and monitoring capabilities

Happy coding! 🎉

This MCP server demonstrates a complete implementation from zero to hero. Use it as a foundation for building your own MCP servers!