Donts MCP Server Demo

🚀 MCP Server Demo Project

This is a demonstration project of a Model Context Protocol (MCP) server based on Spring Boot. It offers functionalities such as a calculator, weather query, and tools for data models and API interfaces.

🚀 Quick Start

Prerequisites

• JDK 17 or higher
• Maven 3.6 or higher
• QWeather API key (required for the weather query function)

Configuration

1. Clone the project to your local machine.
2. Configure the QWeather API key in src/main/resources/application.yml.

Build and Run

# Compile the project
mvn clean package

# Run the project
java -jar target/donts-ai-0.0.1-SNAPSHOT.jar

✨ Features

This project is a simple implementation of an MCP server built with Spring Boot and WebFlux, offering the following features:

1. Calculator Tool - Capable of calculating mathematical expressions.
2. Weather Query Tool - Enables querying real - time weather for a specified city.
3. System Information Resource - Provides basic system information.
4. Data Model Search Tool - Searches for matching data models based on user descriptions.
5. API Interface Search Tool - Finds corresponding API interfaces based on data models.
6. API Execution Tool - Constructs parameters according to user input and invokes actual interfaces.

📦 Installation

Prerequisites

• JDK 17 or higher
• Maven 3.6 or higher
• QWeather API key (for weather query feature)

Configuration

1. Clone the project to your local environment.
2. Configure the QWeather API key in src/main/resources/application.yml.

Build and Run

# Compile the project
mvn clean package

# Run the project
java -jar target/donts-ai-0.0.1-SNAPSHOT.jar

💻 Usage Examples

Calculator Tool

The calculator tool can handle various mathematical expressions, including:

• Basic arithmetic operations (addition, subtraction, multiplication, division)
• Calculation of complex expressions

Examples:

2 + 2
(3 * 4) / 2
sqrt(16) + 5

Weather Query Tool

The weather query tool can retrieve real - time weather information for a specified city.

System Information Resource

The system information resource provides the following basic information:

• Operating system version
• Java Runtime Environment version
• Application runtime
• Current user information

Data Model Search Tool

The data model search tool can search for and return matching data models based on user descriptions or keywords.

Example input:

{
  "description": "用于预测股票价格",
  "keywords": ["时间序列", "回归"]
}

API Interface Search Tool

The API interface search tool can search for and return corresponding API interface information based on the name or function of a data model.

Example input:

{
  "model_name": "用户行为分析模型"
}

API Execution Tool

The API execution tool can construct requests and invoke corresponding API interfaces according to user - input parameters.

Example input:

{
  "url": "http://example.com/api",
  "method": "POST",
  "headers": {
    "Content-Type": "application/json"
  },
  "body": {
    "name": "test",
    "value": "123"
  }
}

Mock Data Cases

User Model

{
  "model_name": "用户行为分析模型",
  "description": "用于分析用户的点击流数据",
  "version": "1.0.0"
}

Order Model

{
  "model_name": "订单预测模型",
  "description": "用于预测未来的订单量",
  "version": "2.1.0"
}

📚 Documentation

API Endpoints

SSE Connection

• Endpoint: /sse
• Method: GET
• Description: Establish an SSE connection to receive server - sent events.

Message Sending

• Endpoint: /mcp/messages
• Method: POST
• Description: Send messages to the MCP server.

🔧 Technical Details

Technology Stack

• Java 17
• Spring Boot
• Spring WebFlux
• Model Context Protocol (MCP)
• Server - Sent Events (SSE)

System Architecture

The main components of this project include:

• MCP Server - Responsible for handling client requests and responses.
• Tool Implementations - Include functional modules such as a calculator, weather query, and data model search.
• API Interfaces - Provide RESTful API services and support SSE event pushing.

🤝 Contribution Guidelines

Welcome to contribute to the project! Please follow these steps:

1. Fork this repository.
2. Create your feature branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add some 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 - see the LICENSE file for details.