Dan Vega Courses

🚀 Spring AI MCP Course Information Server

This repository contains a Spring Boot-based application that implements a Model Control Protocol (MCP) server to provide course information. The application creates a lightweight server that exposes course data through the Spring AI MCP framework, enabling AI models to interact with custom data services and use standardized tools.

The server offers two main tools:

• A tool for retrieving all available courses
• A tool for searching for specific courses by title

This implementation is an excellent starting point for creating your own Model Control Protocol server or integrating external data sources with AI models through Spring AI.

📦 Installation

Project Requirements

• Java 24
• Maven 3.8+
• Spring Boot 3.4.4
• Spring AI 1.0.0-M6

Dependencies

The project depends on the following key dependencies:

• Spring AI MCP Server: Provides the foundation for creating an MCP-compatible server

  <dependency>
      <groupId>org.springframework.ai</groupId>
      <artifactId>spring-ai-mcp-server-spring-boot-starter</artifactId>
  </dependency>
  

• Spring Boot Starter Web for Demonstration: Provides web components to build an MVC application

  <dependency>
      <groupId>org.springframework.boot</groupId>
      <artifactId>spring-boot-starter-web</artifactId>
  </dependency>
  

🚀 Quick Start

1. Clone the repository

   git clone https://github.com/your-username/spring-ai-mcp.git
   cd spring-ai-mcp
   

2. Build the project

   mvn clean install
   

3. Run the application

   java -jar target/courses-0.0.1-SNAPSHOT.jar
   

📚 Documentation

Introduction

MCP (Model Control Protocol) is a protocol for establishing communication between AI models and external data sources. Through Spring AI, you can easily expose these services as tools for AI models to call.

Project Structure

src/main/java/
├── CourseService.java       # Business logic for providing course data
└── MCPServerApplication.java # Main application class to start the Spring Boot application

Feature Implementation

1. Create a Service Class

import org.springframework.stereotype.Service;

@Service
public class CourseService {
    public List<Course> getAllCourses() {
        return List.of(
            new Course(1L, "Introduction to Java"),
            new Course(2L, "Advanced Python Programming")
        );
    }

    @Tool(name = "search_courses", description = "Search for courses containing a keyword")
    public List<Course> searchCourses(String keyword) {
        // Add search logic here
        return this.getAllCourses().stream()
            .filter(course -> course.getTitle().toLowerCase().contains(keyword.toLowerCase()))
            .collect(Collectors.toList());
    }
}

2. Create a Course Data Transfer Object (DTO)

import java.util.Objects;

public record Course(
    Long id,
    String title
) {
    @Override
    public boolean equals(Object o) {
        if (this == o) return true;
        if (o == null || getClass() != o.getClass()) return false;
        Course course = (Course) o;
        return Objects.equals(id, course.id);
    }

    @Override
    public int hashCode() {
        return Objects.hash(id);
    }
}

Configure the MCP Server

Configure the following in the application.properties file:

# Set the port of the MCP server
server.port = 8080

# Other Spring Boot configurations...

💻 Usage Examples

Basic Usage

• Get all courses

  curl http://localhost:8080/courses
  

• Search for courses

  curl "http://localhost:8080/search?keyword=Java"
  

Conclusion

Through this example, you can see how to use Spring AI's MCP server to expose custom services. This is very useful for any backend service that needs to interact with AI models.

For more detailed information, please refer to the official documentation.