About MCP Server using Spring Boot Java
A Spring Boot, Java 21, and Spring AI MCP server example for developers building user-management capabilities for AI assistants. It provides synchronous tools for querying and changing user data over standard I/O or SSE.
Key features
- 01User management tools
- 02Paginated queries, search, and CRUD
- 03Synchronous communication
- 04Standard I/O and SSE transports
- 05User data via DummyJSON
Use cases
- 01Provide user queries to an AI client
- 02Find and update users by ID
- 03Test different MCP transports
MCP support
The MCP server exposes tools for querying, searching, adding, updating, and deleting users. It supports standard I/O and SSE transports.
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 READMEMCP Server using Spring Boot Java
A Model Context Protocol (MCP) server implementation built with Spring Boot and Java 21. This project demonstrates how to create an MCP server that provides user management tools for AI assistants.
Features
- Implements MCP server functionality using Spring AI
- Exposes user management tools via MCP
- Synchronous communication mode
- Support for Standard I/O and Server-Sent Events transports
- Integrates with DummyJSON external API for user data
Technologies
- Java 21
- Spring Boot 3.4.3
- Spring AI (Model Context Protocol)
- Project Lombok
- Maven
Getting Started
Prerequisites
- Java 21 or higher
- Maven
Installation
- Clone the repository
git clone https://github.com/yourusername/mcp-spring-java.git
cd mcp-spring-java
- Build the project
mvn clean package
- Run the application
java -jar target/mcp-spring-java-0.0.1-SNAPSHOT.jar
Configuration
The MCP server is configured in application.yml:
- Server runs on port 8090
- Server name: my-dummy-users-server
- Synchronous communication mode
- Supports STDIO transport for terminal-based communication
- Exposes
/mcp/messageendpoint for SSE communication
Available Tools
The server exposes the following user management tools:
getAllUsers- Get all users with paginationgetAllUsersDefault- Get all users with default paginationgetUserById- Get a single user by IDsearchUsers- Search for users by queryaddUser- Add a new userupdateUser- Update a userdeleteUser- Delete a user
Testing with Postman
You can use Postman to test the MCP server endpoints:
-
Start the MCP server
-
Open Postman and create a new request:
- Method: POST
- URL: http://localhost:8090/mcp/message
- Headers:
- Content-Type: application/json
- Accept: application/json
-
For the request body, use the following JSON format to invoke any of the available tools:
{
"message": {
"toolCalls": [
{
"id": "call-123",
"name": "[TOOL_NAME]",
"parameters": {
"[PARAMETER_NAME]": "[PARAMETER_VALUE]"
}
}
]
}
}
Example Requests
Get All Users (Default Pagination)
{
"message": {
"toolCalls": [
{
"id": "call-123",
"name": "getAllUsersDefault",
"parameters": {}
}
]
}
}
Get User by ID
{
"message": {
"toolCalls": [
{
"id": "call-123",
"name": "getUserById",
"parameters": {
"id": 1
}
}
]
}
}
Search Users
{
"message": {
"toolCalls": [
{
"id": "call-123",
"name": "searchUsers",
"parameters": {
"query": "John"
}
}
]
}
}
The response will contain a JSON object with the results from the tool execution.
Usage with MCP Clients
You can configure this server in MCP client applications using the following configuration:
{
"mcpServers": {
"dummy-user-server": {
"command": "java",
"args": [
"-Dspring.ai.mcp.server.stdio=true",
"-Dspring.main.web-application-type=none",
"-Dlogging.pattern.console=",
"-jar",
"path/to/mcp-spring-java-0.0.1-SNAPSHOT.jar"
]
}
}
}
License
This project is licensed under the terms provided in the LICENSE file.
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.