Spring AI快速创建MCP服务

配置文件

首先引入Spring AI的依赖，Java版本要求最低17

pom.xml

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.4.3</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.zhaochao</groupId>
    <artifactId>mcp-server-app</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>mcp-server-app</name>
    <description>mcp-server-app</description>
    <url/>
    <licenses>
        <license/>
    </licenses>
    <developers>
        <developer/>
    </developers>
    <scm>
        <connection/>
        <developerConnection/>
        <tag/>
        <url/>
    </scm>
    <properties>
        <java.version>17</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-starter-mcp-server-webmvc</artifactId>
            <version>1.0.0-M8</version>
        </dependency>
    </dependencies>


    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <configuration>
                    <mainClass>com.zhaochao.mcpserverapp.McpServerAppApplication</mainClass>
                </configuration>
                <executions>
                    <execution>
                        <goals>
                            <goal>repackage</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

stdio默认是关闭的，默认是走SSE模式的

application.yaml

server:
  port: 8000
spring:
  application:
    name: "mcp-server"
  ai:
    mcp:
      server:
        stdio: false
        name: location-mcp-server
        version: 0.0.1

代码实现

编写一个测试的tools

com.zhaochao.mcpserverapp.service.JdbcQueryService

package com.zhaochao.mcpserverapp.service;

import org.springframework.ai.tool.annotation.Tool;
import org.springframework.ai.tool.annotation.ToolParam;
import org.springframework.stereotype.Service;

@Service
public class JdbcQueryService {
    @Tool(description = "查询天气预报")
    public String getWeather(@ToolParam(description = "城市位置") String location){
        return location + "现在的天气是：晴，28°";
    }
}

添加配置文件，将编写的tools方法抛出去

com.zhaochao.mcpserverapp.config.McpConfig

package com.zhaochao.mcpserverapp.config;

import com.zhaochao.mcpserverapp.service.JdbcQueryService;
import org.springframework.ai.tool.ToolCallbackProvider;
import org.springframework.ai.tool.method.MethodToolCallbackProvider;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;

@Configuration
public class McpConfig {
    @Bean
    ToolCallbackProvider toolCallbackProvider(JdbcQueryService jdbcQueryService) {
        return MethodToolCallbackProvider.builder().toolObjects(jdbcQueryService).build();
    };
}

测试结果

项目可以直接运行，或者生成jar包后运行，可以使用post man先测试http://localhost:8000/sse接口是否可以正常连接

然后在任意的模型调用平台配置MCP相关服务，就可以正常调用了，模型会自动识别到该MCP服务下有多少tools