rrezartprebreza/mcp-server
> Use when building MCP (Model Context Protocol) servers in Java/Spring Boot. Covers tool registration, resource exposure, prompt templates, and production deployment using the official MCP Java SDK. Use when user mentions MCP, AI agent integration, or tool calling.
npx skills add https://github.com/rrezartprebreza/spring-boot-skills --skill mcp-server
Official Java SDK: https://github.com/modelcontextprotocol/java-sdk
Maintained by Anthropic in collaboration with Spring AI.
The standalone SDK reached 1.0.0 GA (io.modelcontextprotocol.sdk:mcp). Most Spring Boot
apps should use the Spring AI MCP starter instead — it auto-configures the server, transport,
and tool scanning. The starter coordinates were renamed at Spring AI 1.0 GA to spring-ai-starter-mcp-server-*.
<!-- Recommended for Spring Boot: pick ONE transport starter -->
<!-- stdio (Claude Desktop / Claude Code launching the jar locally) -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-mcp-server</artifactId>
</dependency>
<!-- OR remote HTTP (SSE + Streamable-HTTP) over Spring MVC -->
<dependency>
<groupId>org.springframework.ai</groupId>
<artifactId>spring-ai-starter-mcp-server-webmvc</artifactId>
</dependency>
<!-- OR reactive: spring-ai-starter-mcp-server-webflux -->
<!-- Or drive the raw SDK directly (no Spring AI), now at 1.0.0 GA -->
<dependency>
<groupId>io.modelcontextprotocol.sdk</groupId>
<artifactId>mcp</artifactId>
<version>1.0.0</version>
</dependency>
> The old spring-ai-mcp-server-spring-boot-starter name is dead. GA is spring-ai-starter-mcp-server
> (stdio), -webmvc (servlet SSE / Streamable-HTTP), and -webflux (reactive).
@SpringBootApplication
public class OrderMcpServer {
public static void main(String[] args) {
var transport = new StdioServerTransportProvider();
var server = McpServer.sync(transport)
.serverInfo("order-service-mcp", "1.0.0")
.capabilities(ServerCapabilities.builder().tools(true).resources(true).build())
.tools(getOrderTool(), listOrdersTool())
.build();
Runtime.getRuntime().addShutdownHook(new Thread(server::close));
}
}
// Tool with typed input/output
private static McpServerFeatures.SyncToolSpecification getOrderTool() {
var schema = """
{
"type": "object",
"properties": {
"orderId": { "type": "string", "description": "UUID of the order" }
},
"required": ["orderId"]
}
""";
return McpServerFeatures.SyncToolSpecification.builder()
.tool(Tool.builder()
.name("get_order")
.description("Get a single order by ID including all line items and status history")
.inputSchema(schema)
.build())
.callHandler((exchange, args) -> {
String orderId = (String) args.get("orderId");
try {
Order order = orderService.findById(UUID.fromString(orderId));
return new CallToolResult(List.of(
new TextContent(objectMapper.writeValueAsString(order))
), false);
} catch (EntityNotFoundException e) {
return new CallToolResult(List.of(
new TextContent("Order not found: " + orderId)
), true); // isError = true
}
})
.build();
}
This Boot 3 example uses Spring AI's @Tool plus MethodToolCallbackProvider integration. That is
different from the native MCP annotation path used by the Boot 4 / Spring AI 2.0 version, where
@McpTool and @McpToolParam are preferred. Do not mix the two registration styles in one server.
@Configuration
public class McpToolsConfig {
@Bean
public ToolCallbackProvider orderTools(OrderService orderService, ObjectMapper objectMapper) {
return MethodToolCallbackProvider.builder()
.toolObjects(new OrderMcpTools(orderService, objectMapper))
.build();
}
}
@Component
public class OrderMcpTools {
private final OrderService orderService;
private final ObjectMapper objectMapper;
// Spring AI annotation-based tool registration
@Tool(description = "Get order by ID with full line items and status history")
public String getOrder(@ToolParam(description = "UUID of the order") String orderId) {
try {
Order order = orderService.findById(UUID.fromString(orderId));
return objectMapper.writeValueAsString(OrderResponse.from(order));
} catch (Exception e) {
return "Error: " + e.getMessage();
}
}
@Tool(description = "List orders for a customer, optionally filtered by status")
public String listOrders(
@ToolParam(description = "Customer email address") String email,
@ToolParam(description = "Filter by status: PENDING, PROCESSING, SHIPPED, DELIVERED", required = false) String status
) {
List<Order> orders = status != null
? orderService.findByEmailAndStatus(email, OrderStatus.valueOf(status))
: orderService.findByEmail(email);
return objectMapper.writeValueAsString(orders.stream().map(OrderResponse::from).toList());
}
}
spring:
ai:
mcp:
server:
name: order-service-mcp
version: 1.0.0
type: SYNC # SYNC (blocking) or ASYNC (reactive / WebFlux)
# --- stdio: needs spring-ai-starter-mcp-server + banner/console logging OFF ---
stdio: true # framing is over stdin/stdout — nothing else may write there
# --- remote: needs the -webmvc or -webflux starter instead ---
# protocol: STREAMABLE # SSE | STREAMABLE | STATELESS (Streamable-HTTP is the 2025-06-18 default)
> stdio servers must keep stdout clean. Any log line, banner, or System.out.println corrupts
> the JSON-RPC framing and the client silently drops the connection. For stdio, set
> spring.main.banner-mode=off and route logging to a file or stderr.
@Bean
public List<McpServerFeatures.SyncResourceSpecification> mcpResources(OrderRepository repo) {
return List.of(
McpServerFeatures.SyncResourceSpecification.builder()
.resource(Resource.builder()
.uri("orders://recent")
.name("Recent Orders")
.description("Last 50 orders across all customers")
.mimeType("application/json")
.build())
.readHandler((exchange, request) -> {
List<Order> recent = repo.findTop50ByOrderByCreatedAtDesc();
return new ReadResourceResult(List.of(
new TextResourceContents(request.uri(),
objectMapper.writeValueAsString(recent), "application/json")
));
})
.build()
);
}
{
"mcpServers": {
"order-service": {
"command": "java",
"args": ["-jar", "/path/to/order-mcp-server.jar"],
"env": {
"SPRING_DATASOURCE_URL": "jdbc:postgresql://localhost:5432/orders"
}
}
}
}
// Always return structured errors — never throw from tool handlers
private CallToolResult safeExecute(Supplier<Object> action) {
try {
return new CallToolResult(
List.of(new TextContent(objectMapper.writeValueAsString(action.get()))),
false
);
} catch (EntityNotFoundException e) {
return errorResult("NOT_FOUND", e.getMessage());
} catch (Exception e) {
log.error("Tool execution failed", e);
return errorResult("INTERNAL_ERROR", "Unexpected error occurred");
}
}
private CallToolResult errorResult(String code, String message) {
return new CallToolResult(
List.of(new TextContent(String.format("{\"error\":\"%s\",\"message\":\"%s\"}", code, message))),
true // isError flag — agent knows this is an error
);
}
spring-ai-mcp-server-spring-boot-starter name — GA is spring-ai-starter-mcp-server[-webmvc|-webflux]0.9.0 — the standalone SDK is 1.0.0 GA (or just use the Spring AI starter)isError = true in error results — agent can't distinguish errors from dataFetchType.EAGER inside tool handlers — triggers N+1, use projectionsshutdown hooks — always close the server on JVM shutdownstdio for local tools (Claude Code, Claude Desktop); -webmvc/-webflux + Streamable-HTTP for remoteTake rrezartprebreza/mcp-server from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.