refactor(mcp): update to use Spring Boot autoconfiguration and rename tool callbacks

Update MCP examples to use Spring Boot autoconfiguration instead of manual configuration.
Replace deprecated defaultTools method with defaultToolCallbacks across all examples.
Update documentation to reflect these changes and provide more detailed configuration examples.

- Update API from defaultTools to defaultToolCallbacks in all MCP examples
- Update README files with more detailed configuration examples

Signed-off-by: Christian Tzolov <[email protected]>

Author: tzolov

model-context-protocol/brave/README.md

@@ -1,6 +1,6 @@
 # Spring AI - Model Context Protocol (MCP) Brave Search Example
 
-This example demonstrates how to create a Spring AI Model Context Protocol (MCP) client that communicates with the [Brave Search MCP Server](https://github.com/modelcontextprotocol/servers/tree/main/src/brave-search). The application shows how to build an MCP client that enables natural language interactions with Brave Search, allowing you to perform internet searches through a conversational interface. Instead of using Spring Boot autoconfiguration, this example demonstrates how to manually configure the MCP client transport using an `@Bean` definition.
+This example demonstrates how to create a Spring AI Model Context Protocol (MCP) client that communicates with the [Brave Search MCP Server](https://github.com/modelcontextprotocol/servers/tree/main/src/brave-search). The application shows how to build an MCP client that enables natural language interactions with Brave Search, allowing you to perform internet searches through a conversational interface. This example uses Spring Boot autoconfiguration to set up the MCP client through configuration files.
 
 When run, the application demonstrates the MCP client's capabilities by asking a specific question: "Does Spring AI supports the Model Context Protocol? Please provide some references." The MCP client uses Brave Search to find relevant information and returns a comprehensive answer. After providing the response, the application exits.
 
@@ -52,56 +52,46 @@ The application will execute a single query asking about Spring AI's support for
 
 ## How it Works
 
-The application integrates Spring AI with the Brave Search MCP server through several components:
+The application integrates Spring AI with the Brave Search MCP server through Spring Boot autoconfiguration:
 
-### MCP Client Setup
+### MCP Client Configuration
 
-```java
-@Bean
-public McpSyncClient mcpClient() {
-
-   // https://github.com/modelcontextprotocol/servers/tree/main/src/brave-search
-   var stdioParams = ServerParameters.builder("npx")
-           .args("-y", "@modelcontextprotocol/server-brave-search")
-           .addEnvVar("BRAVE_API_KEY", System.getenv("BRAVE_API_KEY"))
-           .build();
-
-   var mcpClient = McpClient.sync(new StdioClientTransport(stdioParams)).build();
-   var init = mcpClient.initialize();
-   logger.info("MCP Initialized: {}", init);
-   return mcpClient;
-}
-```
-
-The MCP client is configured to:
-1. Use the Brave Search MCP server via npx
-2. Pass the Brave API key from environment variables
-3. Initialize a synchronous connection to the server
+The MCP client is configured using configuration files:
 
-### Function Callbacks
-
-The application automatically discovers and registers available Brave Search tools:
+1. `application.properties`:
+```properties
+spring.ai.mcp.client.stdio.servers-configuration=classpath:/mcp-servers-config.json
+```
 
-```java
-List<McpFunctionCallback> functionCallbacks = mcpClient.listTools(null)
-        .tools()
-        .stream()
-        .map(tool -> new McpFunctionCallback(mcpClient, tool))
-        .toList();
+2. `mcp-servers-config.json`:
+```json
+{
+  "mcpServers": {
+    "brave-search": {
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-brave-search"
+      ],
+      "env": {
+      }
+    }
+  }
+}
 ```
 
-These callbacks enable the ChatClient to:
-- Access Brave Search tools during conversations
-- Handle function calls requested by the AI model
-- Execute search queries against the Brave Search API
+This configuration:
+1. Uses the Brave Search MCP server via npx
+2. The Brave API key is passed from environment variables
+3. Initializes a synchronous connection to the server
 
 ### Chat Integration
 
-The ChatClient is configured with the Brave Search function callbacks:
+The ChatClient is configured with the MCP tool callbacks in the Application class:
 
 ```java
 var chatClient = chatClientBuilder
-        .defaultFunctions(functionCallbacks.toArray(new McpFunctionCallback[0]))
+        .defaultToolCallbacks(new SyncMcpToolCallbackProvider(mcpSyncClients))
         .build();
 ```
 

model-context-protocol/brave/src/main/java/org/springframework/ai/mcp/samples/brave/Application.java

@@ -11,7 +11,6 @@
 import org.springframework.boot.CommandLineRunner;
 import org.springframework.boot.SpringApplication;
 import org.springframework.boot.autoconfigure.SpringBootApplication;
-import org.springframework.context.ConfigurableApplicationContext;
 import org.springframework.context.annotation.Bean;
 
 @SpringBootApplication
@@ -20,24 +19,22 @@ public class Application {
 	private static final Logger logger = LoggerFactory.getLogger(Application.class);
 
 	public static void main(String[] args) {
-		SpringApplication.run(Application.class, args);
+		SpringApplication.run(Application.class, args).close();
 	}
 
 	@Bean
 	public CommandLineRunner predefinedQuestions(ChatClient.Builder chatClientBuilder,
-		List<McpSyncClient> mcpSyncClients, ConfigurableApplicationContext context) {
+		List<McpSyncClient> mcpSyncClients) {
 
 		return args -> {
 
 			var chatClient = chatClientBuilder
-					.defaultTools(new SyncMcpToolCallbackProvider(mcpSyncClients))
+					.defaultToolCallbacks(new SyncMcpToolCallbackProvider(mcpSyncClients))
 					.build();
 
 			String question = "Does Spring AI supports the Model Context Protocol? Please provide some references.";
 			logger.info("QUESTION: {}\n", question);
 			logger.info("ASSISTANT: {}\n", chatClient.prompt(question).call().content());
-
-			context.close();
 		};
 	}
 }

model-context-protocol/client-starter/starter-default-client/README.md

@@ -6,7 +6,7 @@ Follow the [MCP Client Boot Starter](https://docs.spring.io/spring-ai/reference/
 
 ## Overview
 
-The project uses Spring Boot and Spring AI to create a command-line application that demonstrates MCP server integration. The application:
+The project uses Spring Boot 3.3.6 and Spring AI 1.0.0-SNAPSHOT to create a command-line application that demonstrates MCP server integration. The application:
 - Connects to MCP servers using STDIO and/or SSE (HttpClient-based) transports
 - Integrates with Spring AI's chat capabilities
 - Demonstrates tool execution through MCP servers
@@ -19,7 +19,7 @@ For example, running the application with `-Dai.user.input="Does Spring AI suppo
 - Java 17 or later
 - Maven 3.6+
 - Anthropic API key (Claude) (Get one at https://docs.anthropic.com/en/docs/initial-setup)
-- Brave Search API key (Get one at https://brave.com/search/api/)
+- Brave Search API key (for the Brave Search MCP server) (Get one at https://brave.com/search/api/)
 
 ## Dependencies
 
@@ -54,6 +54,9 @@ spring.main.web-application-type=none
 
 # AI Provider Configuration
 spring.ai.anthropic.api-key=${ANTHROPIC_API_KEY}
+
+# Enable the MCP client tool-callback auto-configuration
+spring.ai.mcp.client.toolcallback.enabled=true
 ```
 
 #### STDIO Transport Properties
@@ -117,10 +120,12 @@ The application demonstrates a simple command-line interaction with an AI model
 
 ## Running the Application
 
-1. Set the required environment variable:
+1. Set the required environment variables:
    ```bash
    export ANTHROPIC_API_KEY=your-api-key
-   export BRAVE_API_KEY='your-brave-api-key-here'
+   
+   # For the Brave Search MCP server
+   export BRAVE_API_KEY=your-brave-api-key
    ```
 
 2. Build the application:
@@ -130,10 +135,14 @@ The application demonstrates a simple command-line interaction with an AI model
 
 3. Run the application:
    ```bash   
+   # Run with the default question from application.properties
+   java -jar target/mcp-starter-default-client-0.0.1-SNAPSHOT.jar
+   
+   # Or specify a custom question
    java -Dai.user.input='Does Spring AI support MCP?' -jar target/mcp-starter-default-client-0.0.1-SNAPSHOT.jar
    ```
 
-The application will execute the question "Does Spring AI support MCP?", use the provided brave (or other tools) to answer it, and display the AI assistant's response.
+The application will execute the question, use the configured MCP tools to answer it, and display the AI assistant's response.
 
 ## Additional Resources
 

model-context-protocol/client-starter/starter-default-client/src/main/java/org/springframework/ai/mcp/samples/client/Application.java

@@ -41,7 +41,7 @@ public CommandLineRunner predefinedQuestions(ChatClient.Builder chatClientBuilde
 		return args -> {
 
 			var chatClient = chatClientBuilder
-					.defaultTools(tools)
+					.defaultToolCallbacks(tools)
 					.build();
 
 			System.out.println("\n>>> QUESTION: " + userInput);

model-context-protocol/client-starter/starter-webflux-client/README.md

@@ -6,20 +6,21 @@ Follow the [MCP Client Boot Starter](https://docs.spring.io/spring-ai/reference/
 
 ## Overview
 
-The project uses Spring Boot and Spring AI to create a command-line application that demonstrates MCP server integration with WebFlux. The application:
+The project uses Spring Boot 3.3.6 and Spring AI 1.0.0-SNAPSHOT to create a command-line application that demonstrates MCP server integration with WebFlux. The application:
 - Connects to MCP servers using STDIO and/or SSE (WebFlux-based) transports
 - Integrates with Spring AI's chat capabilities
 - Demonstrates tool execution through MCP servers
 - Takes a user-defined question via the `-Dai.user.input` command-line property, which is mapped to a Spring `@Value` annotation in the code
 
-For example, running the application with `-Dai.user.input="Does Spring AI support MCP?"` will inject this question into the application through Spring's property injection, and the application will use it to query the MCP server using WebFlux's reactive programming model.
+For example, running the application with `-Dai.user.input="What tools are available?"` will inject this question into the application through Spring's property injection, and the application will use it to query the MCP server using WebFlux's reactive programming model.
 
 ## Prerequisites
 
 - Java 17 or later
 - Maven 3.6+
 - Anthropic API key (Claude) (Get one at https://docs.anthropic.com/en/docs/initial-setup)
-- Brave Search API key (Get one at https://brave.com/search/api/)
+- OpenAI API key (optional, commented out by default) (Get one at https://platform.openai.com/api-keys)
+- Brave Search API key (for the Brave Search MCP server) (Get one at https://brave.com/search/api/)
 
 ## Dependencies
 
@@ -35,6 +36,11 @@ The project uses the following main dependencies:
         <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-starter-model-anthropic</artifactId>
     </dependency>
+    <!-- OpenAI dependency is commented out by default but can be enabled -->
+    <!-- <dependency>
+        <groupId>org.springframework.ai</groupId>
+        <artifactId>spring-ai-starter-model-openai</artifactId>
+    </dependency> -->
 </dependencies>
 ```
 
@@ -54,6 +60,10 @@ spring.main.web-application-type=none
 
 # AI Provider Configuration
 spring.ai.anthropic.api-key=${ANTHROPIC_API_KEY}
+spring.ai.openai.api-key=${OPENAI_API_KEY}
+
+# Enable the MCP client tool-callback auto-configuration
+spring.ai.mcp.client.toolcallback.enabled=true
 ```
 
 #### STDIO Transport Properties
@@ -111,16 +121,19 @@ The application demonstrates a simple command-line interaction with an AI model
 
 1. The application starts and configures multiple MCP Clients (one for each provided STDIO or SSE connection configuration)
 2. It builds a ChatClient with the configured MCP tools
-3. Sends a predefined question (set vi the `ai.user.input` property) to the AI model
+3. Sends a predefined question (set via the `ai.user.input` property) to the AI model
 4. Displays the AI's response
 5. Automatically closes the application
 
 ## Running the Application
 
-1. Set the required environment variable:
+1. Set the required environment variables:
    ```bash
    export ANTHROPIC_API_KEY=your-api-key
-   export BRAVE_API_KEY='your-brave-api-key-here'
+   # If using OpenAI (uncomment the dependency in pom.xml first)
+   # export OPENAI_API_KEY=your-openai-api-key
+   # For the Brave Search MCP server
+   export BRAVE_API_KEY=your-brave-api-key
    ```
 
 2. Build the application:
@@ -130,10 +143,14 @@ The application demonstrates a simple command-line interaction with an AI model
 
 3. Run the application:
    ```bash   
+   # Run with the default question from application.properties
+   java -jar target/mcp-starter-webflux-client-0.0.1-SNAPSHOT.jar
+   
+   # Or specify a custom question
    java -Dai.user.input='Does Spring AI support MCP?' -jar target/mcp-starter-webflux-client-0.0.1-SNAPSHOT.jar
    ```
 
-The application will execute the question "Does Spring AI support MCP?", use the provided brave (or other tools) to answer it, and display the AI assistant's response.
+The application will execute the question, use the configured MCP tools to answer it, and display the AI assistant's response.
 
 ## Additional Resources
 

model-context-protocol/client-starter/starter-webflux-client/src/main/java/org/springframework/ai/mcp/samples/client/Application.java

@@ -41,7 +41,7 @@ public CommandLineRunner predefinedQuestions(ChatClient.Builder chatClientBuilde
 		return args -> {
 
 			var chatClient = chatClientBuilder
-					.defaultTools(tools)
+					.defaultToolCallbacks(tools)
 					.build();
 
 			System.out.println("\n>>> QUESTION: " + userInput);