MCP 服务器注释
MCP 服务器注释为使用 Java 注释实现 MCP 服务器功能提供了声明式方式。 这些注释简化了工具、资源、提示和完成处理程序的创建。
服务器注释
@McpTool
这@McpTool注释标记方法为MCP工具实现,并自动生成JSON模式。
基本用途
@Component
public class CalculatorTools {
@McpTool(name = "add", description = "Add two numbers together")
public int add(
@McpToolParam(description = "First number", required = true) int a,
@McpToolParam(description = "Second number", required = true) int b) {
return a + b;
}
}
高级功能
@McpTool(name = "calculate-area",
description = "Calculate the area of a rectangle",
annotations = McpTool.McpAnnotations(
title = "Rectangle Area Calculator",
readOnlyHint = true,
destructiveHint = false,
idempotentHint = true
))
public AreaResult calculateRectangleArea(
@McpToolParam(description = "Width", required = true) double width,
@McpToolParam(description = "Height", required = true) double height) {
return new AreaResult(width * height, "square units");
}
附请求上下文
工具可以访问高级作的请求上下文:
@McpTool(name = "process-data", description = "Process data with request context")
public String processData(
McpSyncRequestContext context,
@McpToolParam(description = "Data to process", required = true) String data) {
// Send logging notification
context.info("Processing data: " + data);
// Send progress notification (using convenient method)
context.progress(p -> p.progress(0.5).total(1.0).message("Processing..."));
// Ping the client
context.ping();
return "Processed: " + data.toUpperCase();
}
动态模式支持
工具可以接受呼叫工具请求对于运行时模式处理:
@McpTool(name = "flexible-tool", description = "Process dynamic schema")
public CallToolResult processDynamic(CallToolRequest request) {
Map<String, Object> args = request.arguments();
// Process based on runtime schema
String result = "Processed " + args.size() + " arguments dynamically";
return CallToolResult.builder()
.addTextContent(result)
.build();
}
进展追踪
工具可以接收进度Tokens以跟踪长期运行的作:
@McpTool(name = "long-task", description = "Long-running task with progress")
public String performLongTask(
McpSyncRequestContext context,
@McpToolParam(description = "Task name", required = true) String taskName) {
// Access progress token from context
String progressToken = context.request().progressToken();
if (progressToken != null) {
context.progress(p -> p.progress(0.0).total(1.0).message("Starting task"));
// Perform work...
context.progress(p -> p.progress(1.0).total(1.0).message("Task completed"));
}
return "Task " + taskName + " completed";
}
@McpResource
这@McpResource注释通过URI模板提供资源访问。
基本用途
@Component
public class ResourceProvider {
@McpResource(
uri = "config://{key}",
name = "Configuration",
description = "Provides configuration data")
public String getConfig(String key) {
return configData.get(key);
}
}
使用 ReadResourceResult
@McpResource(
uri = "user-profile://{username}",
name = "User Profile",
description = "Provides user profile information")
public ReadResourceResult getUserProfile(String username) {
String profileData = loadUserProfile(username);
return new ReadResourceResult(List.of(
new TextResourceContents(
"user-profile://" + username,
"application/json",
profileData)
));
}
附请求上下文
@McpResource(
uri = "data://{id}",
name = "Data Resource",
description = "Resource with request context")
public ReadResourceResult getData(
McpSyncRequestContext context,
String id) {
// Send logging notification using convenient method
context.info("Accessing resource: " + id);
// Ping the client
context.ping();
String data = fetchData(id);
return new ReadResourceResult(List.of(
new TextResourceContents("data://" + id, "text/plain", data)
));
}
@McpPrompt
这@McpPrompt注释为 AI 互动生成提示消息。
基本用途
@Component
public class PromptProvider {
@McpPrompt(
name = "greeting",
description = "Generate a greeting message")
public GetPromptResult greeting(
@McpArg(name = "name", description = "User's name", required = true)
String name) {
String message = "Hello, " + name + "! How can I help you today?";
return new GetPromptResult(
"Greeting",
List.of(new PromptMessage(Role.ASSISTANT, new TextContent(message)))
);
}
}
附带可选参数
@McpPrompt(
name = "personalized-message",
description = "Generate a personalized message")
public GetPromptResult personalizedMessage(
@McpArg(name = "name", required = true) String name,
@McpArg(name = "age", required = false) Integer age,
@McpArg(name = "interests", required = false) String interests) {
StringBuilder message = new StringBuilder();
message.append("Hello, ").append(name).append("!\n\n");
if (age != null) {
message.append("At ").append(age).append(" years old, ");
// Add age-specific content
}
if (interests != null && !interests.isEmpty()) {
message.append("Your interest in ").append(interests);
// Add interest-specific content
}
return new GetPromptResult(
"Personalized Message",
List.of(new PromptMessage(Role.ASSISTANT, new TextContent(message.toString())))
);
}
@McpComplete
这@McpComplete注释为提示提供自动补全功能。
基本用途
@Component
public class CompletionProvider {
@McpComplete(prompt = "city-search")
public List<String> completeCityName(String prefix) {
return cities.stream()
.filter(city -> city.toLowerCase().startsWith(prefix.toLowerCase()))
.limit(10)
.toList();
}
}
使用 CompleteRequest.CompleteArgument
@McpComplete(prompt = "travel-planner")
public List<String> completeTravelDestination(CompleteRequest.CompleteArgument argument) {
String prefix = argument.value().toLowerCase();
String argumentName = argument.name();
// Different completions based on argument name
if ("city".equals(argumentName)) {
return completeCities(prefix);
} else if ("country".equals(argumentName)) {
return completeCountries(prefix);
}
return List.of();
}
与CompleteResult合作
@McpComplete(prompt = "code-completion")
public CompleteResult completeCode(String prefix) {
List<String> completions = generateCodeCompletions(prefix);
return new CompleteResult(
new CompleteResult.CompleteCompletion(
completions,
completions.size(), // total
hasMoreCompletions // hasMore flag
)
);
}
无状态实现与有状态实现
统一请求上下文(推荐)
用McpSyncRequestContext或McpAsync请求上下文对于一个兼容有状态和无状态作的统一接口:
public record UserInfo(String name, String email, int age) {}
@McpTool(name = "unified-tool", description = "Tool with unified request context")
public String unifiedTool(
McpSyncRequestContext context,
@McpToolParam(description = "Input", required = true) String input) {
// Access request and metadata
String progressToken = context.request().progressToken();
// Logging with convenient methods
context.info("Processing: " + input);
// Progress notifications (Note client should set a progress token
// with its request to be able to receive progress updates)
context.progress(50); // Simple percentage
// Ping client
context.ping();
// Check capabilities before using
if (context.elicitEnabled()) {
// Request user input (only in stateful mode)
StructuredElicitResult<UserInfo> elicitResult = context.elicit(UserInfo.class);
if (elicitResult.action() == ElicitResult.Action.ACCEPT) {
// Use elicited data
}
}
if (context.sampleEnabled()) {
// Request LLM sampling (only in stateful mode)
CreateMessageResult samplingResult = context.sample("Generate response");
// Use sampling result
}
return "Processed with unified context";
}
简单作(无上下文)
对于简单的作,你可以完全省略上下文参数:
@McpTool(name = "simple-add", description = "Simple addition")
public int simpleAdd(
@McpToolParam(description = "First number", required = true) int a,
@McpToolParam(description = "Second number", required = true) int b) {
return a + b;
}
轻量级无状态(使用 McpTransportContext)
对于无状态作,需要最少的传输上下文:
@McpTool(name = "stateless-tool", description = "Stateless with transport context")
public String statelessTool(
McpTransportContext context,
@McpToolParam(description = "Input", required = true) String input) {
// Access transport-level context only
// No bidirectional operations (roots, elicitation, sampling)
return "Processed: " + input;
}
| 无状态服务器不支持双向作: |
因此,以下方法McpSyncRequestContext或McpAsync请求上下文在无状态模式下,会被忽略。
按服务器类型进行方法过滤
MCP 注释框架自动根据服务器类型和方法特性过滤注释方法。这确保每个服务器配置只注册合适的方法。 每个过滤方法都会记录警告,以便调试。
同步过滤与异步过滤
同步服务器
同步服务器(配置为spring.ai.mcp.server.type=SYNC)使用以下条件的同步提供者:
-
接受具有非反应性返回类型的方法:
-
原始类型(
智力,双,布尔) -
对象类型(
字符串,整数, 自定义POJOs) -
MCP类型(
呼叫工具结果,ReadResourceResult,GetPromptResult,CompleteResult) -
收藏(
List<String>,Map<String,对象>)
-
-
过滤响应式返回类型的方法:
-
单核细胞增<症> -
Flux<T> -
出版<>
-
@Component
public class SyncTools {
@McpTool(name = "sync-tool", description = "Synchronous tool")
public String syncTool(String input) {
// This method WILL be registered on sync servers
return "Processed: " + input;
}
@McpTool(name = "async-tool", description = "Async tool")
public Mono<String> asyncTool(String input) {
// This method will be FILTERED OUT on sync servers
// A warning will be logged
return Mono.just("Processed: " + input);
}
}
异步服务器
异步服务器(配置为spring.ai.mcp.server.type=ASYNC)使用异步提供者,满足以下条件:
-
接受具有反应返回类型的方法:
-
单核细胞增<症>(针对单一结果) -
Flux<T>(观看直播结果) -
出版<>(通用反应型)
-
-
过滤出具有非反应性返回类型的方法:
-
原始类型
-
对象类型
-
收集
-
MCP结果类型
-
@Component
public class AsyncTools {
@McpTool(name = "async-tool", description = "Async tool")
public Mono<String> asyncTool(String input) {
// This method WILL be registered on async servers
return Mono.just("Processed: " + input);
}
@McpTool(name = "sync-tool", description = "Sync tool")
public String syncTool(String input) {
// This method will be FILTERED OUT on async servers
// A warning will be logged
return "Processed: " + input;
}
}
有状态过滤与无状态过滤
有状态服务器
有状态服务器支持双向通信,并接受以下方法:
-
双向上下文参数:
-
McpSyncRequestContext(用于同步作) -
McpAsync请求上下文(对于异步作) -
McpSyncServerExchange(传统,用于同步作) -
McpAsyncServerExchange(Legacy,用于异步作)
-
-
支持双向作:
-
根()- 访问根目录 -
elicit()- 请求用户输入 -
样本()- 请求LLM采样
-
@Component
public class StatefulTools {
@McpTool(name = "interactive-tool", description = "Tool with bidirectional operations")
public String interactiveTool(
McpSyncRequestContext context,
@McpToolParam(description = "Input", required = true) String input) {
// This method WILL be registered on stateful servers
// Can use elicitation, sampling, roots
if (context.sampleEnabled()) {
var samplingResult = context.sample("Generate response");
// Process sampling result...
}
return "Processed with context";
}
}
无状态服务器
无状态服务器针对简单的请求-响应模式进行了优化,并且:
-
过滤出具有双向上下文参数的方法:
-
方法
McpSyncRequestContext被跳过 -
方法
McpAsync请求上下文被跳过 -
方法
McpSyncServerExchange被跳过 -
方法
McpAsyncServerExchange被跳过 -
每个过滤方法都会记录警告
-
-
接受以下方法:
-
McpTransportContext(轻量级无状态上下文) -
完全没有上下文参数
-
只有普通人
@McpToolParam参数
-
-
不支持双向作:
-
根()- 不可用 -
elicit()- 不可用 -
样本()- 不可用
-
@Component
public class StatelessTools {
@McpTool(name = "simple-tool", description = "Simple stateless tool")
public String simpleTool(@McpToolParam(description = "Input") String input) {
// This method WILL be registered on stateless servers
return "Processed: " + input;
}
@McpTool(name = "context-tool", description = "Tool with transport context")
public String contextTool(
McpTransportContext context,
@McpToolParam(description = "Input") String input) {
// This method WILL be registered on stateless servers
return "Processed: " + input;
}
@McpTool(name = "bidirectional-tool", description = "Tool with bidirectional context")
public String bidirectionalTool(
McpSyncRequestContext context,
@McpToolParam(description = "Input") String input) {
// This method will be FILTERED OUT on stateless servers
// A warning will be logged
return "Processed with sampling";
}
}
过滤摘要
| 服务器类型 | 公认方法 | 滤波方法 |
|---|---|---|
同步状态 |
非反应性回报+双向语境 |
反应回波(单声道/流) |
异步有状态 |
反应性回报(单向/通量)+双向上下文 |
非反应性回报 |
同步无状态 |
非反应性回报 + 无双向语境 |
响应式返回或双向上下文参数 |
异步无状态 |
反应性回波(单向/通量)+无双向上下文 |
非反应性回报或双向上下文参数 |
| 方法过滤的最佳实践: |
-
保持方法与你的服务器类型保持一致——同步服务器用同步方法,异步服务器用异步方法
-
将有状态和无状态实现分为不同类别以便清晰
-
启动时检查日志是否有过滤方法警告
-
使用合适的语境 -
McpSyncRequestContext/McpAsync请求上下文对于有状态的,McpTransportContext代表无国籍者 -
如果你支持有状态和无状态部署,可以测试这两种模式
异步支持
所有服务器注释都支持使用 Reactor 的异步实现:
@Component
public class AsyncTools {
@McpTool(name = "async-fetch", description = "Fetch data asynchronously")
public Mono<String> asyncFetch(
@McpToolParam(description = "URL", required = true) String url) {
return Mono.fromCallable(() -> {
// Simulate async operation
return fetchFromUrl(url);
}).subscribeOn(Schedulers.boundedElastic());
}
@McpResource(uri = "async-data://{id}", name = "Async Data")
public Mono<ReadResourceResult> asyncResource(String id) {
return Mono.fromCallable(() -> {
String data = loadData(id);
return new ReadResourceResult(List.of(
new TextResourceContents("async-data://" + id, "text/plain", data)
));
}).delayElements(Duration.ofMillis(100));
}
}
Spring Boot 集成
通过 Spring Boot 自动配置,带注释的豆子会自动检测并注册:
@SpringBootApplication
public class McpServerApplication {
public static void main(String[] args) {
SpringApplication.run(McpServerApplication.class, args);
}
}
@Component
public class MyMcpTools {
// Your @McpTool annotated methods
}
@Component
public class MyMcpResources {
// Your @McpResource annotated methods
}
自动配置将:
-
扫描带有MCP注释的豆子
-
制定合适的规范
-
向MCP服务器注册
-
根据配置处理同步和异步实现