MCP Server/Client as a proxy to existing Java Spring REST API

README.md

MCP Server/Client as a proxy to existing Java Spring REST API

In this example, we will build a MCP Server/Client as a proxy to existing Java Spring REST API.

Assume an existing Spring Boot REST API app with a ProductController exposing /products endpoints. We'll add MCP support using Spring AI.

1. Add Dependencies (pom.xml):

<dependencies>
    <!-- Existing Spring Boot deps -->
    <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-starter-mcp-server-webmvc</artifactId>
    </dependency>
</dependencies>

2. Configure Properties (application.properties):

spring.ai.mcp.server.enabled=true
spring.ai.mcp.server.name=product-mcp-server
spring.ai.mcp.server.transport=http  # Expose over HTTP

3. Annotate Existing Service:

Assume existing ProductService with methods calling repo or external API.

// Filename: ProductService.java
import org.springframework.ai.mcp.Tool;
import org.springframework.stereotype.Service;
import java.util.List;

@Service
public class ProductService {
    // Existing logic, e.g., repo or REST calls

    @Tool(name = "get_products", description = "Retrieve all products from the existing REST API")
    public List<Product> getProducts() {
        // Existing code: e.g., call repo.findAll() or RestTemplate.getForList("/products")
        return List.of(new Product("1", "Laptop", 999.99));
    }

    @Tool(name = "get_product_by_id", description = "Get a product by ID from the existing REST API")
    public Product getProductById(String id) {
        // Existing code: e.g., repo.findById(id) or RestTemplate.getForObject("/products/" + id)
        return new Product(id, "Product " + id, 100.0);
    }
}

// Filename: Product.java
public record Product(String id, String name, double price) {}

4. Register Tools in Main App:

// Filename: ExistingRestApp.java
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.ai.mcp.ToolCallbacks;
import java.util.List;
import org.springframework.context.annotation.Bean;

@SpringBootApplication
public class ExistingRestApp {

    public static void main(String[] args) {
        SpringApplication.run(ExistingRestApp.class, args);
    }

    @Bean
    public List<ToolCallbacks> productTools(ProductService productService) {
        return List.of(ToolCallbacks.from(productService));
    }
}

5. Run: Start the app. The MCP server exposes tools at the configured endpoint (e.g., HTTP).
6. AI clients can now use get_products etc., leveraging the existing REST logic.