About Cars MCP Server
Cars MCP Server is an example MCP server built with Spring AI for developers learning to register Java service methods as tools. It provides lookup operations for a car wishlist by model name or build year.
Key features
- 01Uses Spring AI ToolCallback
- 02List cars in the wishlist
- 03Find a car by model name
- 04Find a car by build year
Use cases
- 01Learn to register MCP tools with Spring AI
- 02Look up entries in the car wishlist
MCP support
The server exposes CarService methods as tools to MCP clients through Spring AI ToolCallback.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECars MCP Server
This is an MCP (Model Context Protocol) server built using Spring AI. The project demonstrates the use of Spring AI's ToolCallback API to expose tools for interacting with a list of cars, which represents Amarpreet's wishlist.
Demo
Project Structure
The project is organized as follows:
-
src/main/java/com/amarpreet/carsmcpserver/CarsmcpserverApplication.java: The main entry point of the Spring Boot application. It initializes the application and registers theToolCallbackbeans using theCarServiceclass.Car.java: A simplerecordclass representing a car with two fields:modelNameandbuildYear.CarService.java: A service class that provides methods to interact with the list of cars. These methods are exposed as tools using theToolCallbackAPI.
-
src/main/resources/application.properties: Contains configuration properties for the Spring Boot application. -
src/test/java/com/amarpreet/carsmcpserver/CarsmcpserverApplicationTests.java: Contains a basic test to ensure the application context loads correctly.
ToolCallback API
The ToolCallback API is used to expose methods from the CarService class as tools. These tools can be invoked programmatically or through an AI-driven interface. The CarsmcpserverApplication class registers these tools using the ToolCallbacks.from() method.
Tool Registration
In CarsmcpserverApplication.java:
@Bean
public List<ToolCallback> amarpreetTools(CarService carService) {
return List.of(ToolCallbacks.from(carService));
}
This registers all methods annotated with @Tool in the CarService class as ToolCallback instances.
CarService
The CarService class is the core of this application. It manages a list of cars and provides the following methods:
Methods in CarService
getCars()
- Tool Name:
get_cars - Description: Retrieves the list of cars in Amarpreet's wishlist.
- Return Type:
List<Car>
getCar(String name)
- Tool Name:
get_car_by_name - Description: Finds a car by its model name.
- Parameters:
name- The model name to search for.
- Return Type:
Car(ornullif not found)
getCarByYear(Integer year)
- Tool Name:
get_car_by_years - Description: Finds a car by its build year.
- Parameters:
year- The build year to search for.
- Return Type:
Car(ornullif not found)
Initialization
The CarService class initializes a list of cars during application startup using the @PostConstruct annotation:
public void init() {
log.info("Initializing cars MCP server...");
cars.addAll(List.of(
new Car("BMW Neue Klasse", 2025),
new Car("Ferrari EV", 2025),
new Car("Mercedes AMG 4dr EV", 2025),
new Car("Porsche 718 Boxster", 2025)
));
}
How to Run
Build the project using Maven:
mvn clean install
Run the application:
java -jar target/carsmcpserver-0.0.1-SNAPSHOT.jar
Configuration
The application can be configured using the application.properties file located in src/main/resources. Key properties include:
spring.application.name: The name of the application.spring.main.web-application-type: Set tononefor a non-web application.spring.ai.mcp.server: The name of the MCP server.spring.ai.mcp.version: The version of the MCP server.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.