Sprint Boot Sample MCP Server

🚀 Model Context Protocol (MCP) Server Example Implementation - Using Spring Boot

This is an example of a Model Context Protocol (MCP) server implemented using Spring Boot. The server is designed to be used with an MCP inspector for testing and debugging purposes. It provides a simple REST API to interact with the server and demonstrates how to set up a basic Spring Boot application. Unit tests are included to verify the server's functionality.

📋 Table of Contents

• What is MCP?
• Requirements
• Configuration for e.g., Claude Desktop
• Development
  • Debugging
    • Install MCP Inspector
    • Run MCP Inspector for Testing
      • Build MCP Server
      • Run MCP Inspector

🧠 What is MCP?

The Model Context Protocol (MCP) is an open standard that defines how AI models communicate with external tools and data sources. It provides a standard way for AI assistants like Claude to access the following:

• 🌐 Real-time information
• 📊 Custom databases
• 🔄 APIs and services
• 📁 File systems

Think of MCP as the "USB standard for AI" – it provides a common interface that allows any AI model to interact with various tools through a consistent protocol.

Benefits of using Spring Boot:

• 🔄 Seamless integration: Easily expose the application's functionality to AI assistants.
• 🛠️ Tool definition: Define custom tools using simple annotations.
• 🚀 Spring Boot simplicity: Leverage Spring's dependency injection and configuration management.
• 📈 Enhanced AI capabilities: Enable AI models to access an organization's real-time data and services.

Requirements

• Java version 17 or higher
• Maven
• MCP Inspector (optional, for testing)

Configuration for e.g., Claude Desktop

{
  "mcpServers": {
    "sample-mcp-server": {
      "command": "java",
      "args": [
        "-jar",
        "sample-mcp-server-0.0.1-SNAPSHOT.jar",
        "--port",
        "8080",
        "--host",
        "localhost"
      ],
      "env": {
        "JAVA_TOOL_OPTIONS": "-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5005"
      }
    }
  }
}

Note: The JAVA_TOOL_OPTIONS environment variable is used to set JVM options for remote debugging. The address and port can be changed as needed.

💻 Development

Debugging

Install MCP Inspector

npm -g install @modelcontextprotocol/inspector

Run MCP Inspector for Testing

Build MCP Server

mvn clean package

Run MCP Inspector

npx @modelcontextprotocol/inspector -- sample-mcp-server.json

🛠️ Usage Instructions

To use this MCP server, follow these steps:

1. Clone the Repository

git clone https://github.com/your-repository.git
cd mcp-server

2. Build the Project

Run the following command to build the project:

mvn clean install

3. Start the Server

After the build is complete, run the following command to start the server:

java -jar target/mcp-server-0.0.1-SNAPSHOT.jar

4. Test the API

Use curl or other tools to test the REST API. For example:

curl http://localhost:8080/api/test

References

Spring AI extends the capabilities of the MCP Java SDK