Minor MCP ref docs updates

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

Author: tzolov

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/mcp/mcp-annotations-examples.adoc

@@ -214,6 +214,8 @@ public class McpClientApplication {
     public static void main(String[] args) {
         SpringApplication.run(McpClientApplication.class, args);
     }
+
+
 }
 
 @Component
@@ -223,7 +225,7 @@ public class ClientHandlers {
     private final ProgressTracker progressTracker = new ProgressTracker();
     private final ChatModel chatModel;
 
-    public ClientHandlers(ChatModel chatModel) {
+    public ClientHandlers(@Lazy ChatModel chatModel) {
         this.chatModel = chatModel;
     }
 
@@ -661,7 +663,7 @@ public class McpClientHandlers {
 
 === Client Application Setup
 
-The client application configures multiple ChatClient instances for different LLM providers:
+Regisster the MCP tools and handlers in the client application:
 
 [source,java]
 ----
@@ -674,10 +676,9 @@ public class McpClientApplication {
 
     @Bean
     public CommandLineRunner predefinedQuestions(OpenAiChatModel openAiChatModel,
-            List<McpSyncClient> mcpClients) {
+            ToolCallbackProvider mcpToolProvider) {
 
-        return args -> {
-            var mcpToolProvider = new SyncMcpToolCallbackProvider(mcpClients);
+        return args -> {            
 
             ChatClient chatClient = ChatClient.builder(openAiChatModel)
                     .defaultToolCallbacks(mcpToolProvider)
@@ -693,14 +694,6 @@ public class McpClientApplication {
             System.out.println("> ASSISTANT: " + chatClient.prompt(userQuestion).call().content());
         };
     }
-
-    @Bean
-    public Map<String, ChatClient> chatClients(List<ChatModel> chatModels) {
-        return chatModels.stream()
-                .collect(Collectors.toMap(
-                    model -> model.getClass().getSimpleName().toLowerCase(),
-                    model -> ChatClient.builder(model).build()));
-    }
 }
 ----
 

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/mcp/mcp-client-boot-starter-docs.adoc

@@ -264,9 +264,14 @@ spring:
 
 The starter supports two types of clients:
 
-* Synchronous - default client type, suitable for traditional request-response patterns with blocking operations
+* Synchronous - default client type (`spring.ai.mcp.client.type=SYNC`), suitable for traditional request-response patterns with blocking operations
+
+**NOTE:** The SYNC client will register only synchronous MCP annotated methods. Asynchronous methods will be ignored.
+
 * Asynchronous - suitable for reactive applications with non-blocking operations, configured using `spring.ai.mcp.client.type=ASYNC`
 
+**NOTE:** The ASYNC client will register only asynchronous MCP annotated methods. Synchronous methods will be ignored.
+
 === Client Customization
 
 The auto-configuration provides extensive client spec customization capabilities through callback interfaces. These customizers allow you to configure various aspects of the MCP client behavior, from request timeouts to event handling and message processing.

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/mcp/mcp-overview.adoc

@@ -5,7 +5,7 @@ It supports multiple transport mechanisms to provide flexibility across differen
 
 The link:https://modelcontextprotocol.io/sdk/java/mcp-overview[MCP Java SDK] provides a Java implementation of the Model Context Protocol, enabling standardized interaction with AI models and tools through both synchronous and asynchronous communication patterns.
 
-`**Spring AI MCP**` extends the MCP Java SDK with Spring Boot integration, providing both xref:api/mcp/mcp-client-boot-starter-docs.adoc[client] and xref:api/mcp/mcp-server-boot-starter-docs.adoc[server] starters. 
+Spring AI extends the MCP Java SDK with Spring Boot integration, providing both xref:api/mcp/mcp-client-boot-starter-docs.adoc[Client] and xref:api/mcp/mcp-server-boot-starter-docs.adoc[Server] starters and xref:api/mcp/mcp-annotations-overview.adoc[MCP Annotations] for simplified development.
 Bootstrap your AI applications with MCP support using link:https://start.spring.io[Spring Initializer].
 
 == MCP Java SDK Architecture
@@ -93,15 +93,15 @@ Spring AI provides MCP integration through the following Spring Boot starters:
 |Server Type | Dependency | Property
 | xref:api/mcp/mcp-stdio-sse-server-boot-starter-docs.adoc#_sse_webmvc_serve[SSE WebMVC] | `spring-ai-starter-mcp-server-webmvc` | `spring.ai.mcp.server.protocol=SSE` or empty
 | xref:api/mcp/mcp-streamable-http-server-boot-starter-docs.adoc#_streamable_http_webmvc_server[Streamable-HTTP WebMVC] | `spring-ai-starter-mcp-server-webmvc` | `spring.ai.mcp.server.protocol=STREAMABLE`
-| xref:api/mcp/mcp-stateless-server-boot-starter-docs.adoc#_stateless_webmvc_server[Stateless WebMVC] | `spring-ai-starter-mcp-server-webmvc` | `spring.ai.mcp.server.protocol=STATELESS`
+| xref:api/mcp/mcp-stateless-server-boot-starter-docs.adoc#_stateless_webmvc_server[Stateless Streamable-HTTP WebMVC] | `spring-ai-starter-mcp-server-webmvc` | `spring.ai.mcp.server.protocol=STATELESS`
 |===
 
 ==== WebMVC (Reactive)
 |===
 |Server Type | Dependency | Property
 | xref:api/mcp/mcp-stdio-sse-server-boot-starter-docs.adoc#_sse_webflux_serve[SSE WebFlux] | `spring-ai-starter-mcp-server-webflux` | `spring.ai.mcp.server.protocol=SSE` or empty
 | xref:api/mcp/mcp-streamable-http-server-boot-starter-docs.adoc#_streamable_http_webflux_server[Streamable-HTTP WebFlux] | `spring-ai-starter-mcp-server-webflux` | `spring.ai.mcp.server.protocol=STREAMABLE`
-| xref:api/mcp/mcp-stateless-server-boot-starter-docs.adoc#_stateless_webflux_server[Stateless WebFlux] | `spring-ai-starter-mcp-server-webflux` | `spring.ai.mcp.server.protocol=STATELESS`
+| xref:api/mcp/mcp-stateless-server-boot-starter-docs.adoc#_stateless_webflux_server[Stateless Streamable-HTTP WebFlux] | `spring-ai-starter-mcp-server-webflux` | `spring.ai.mcp.server.protocol=STATELESS`
 |===
 
 == xref:api/mcp/mcp-annotations-overview.adoc[Spring AI MCP Annotations]

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/mcp/mcp-server-boot-starter-docs.adoc

@@ -79,10 +79,16 @@ It is designed for straightforward request-response patterns in your application
 To enable this server type, set `spring.ai.mcp.server.type=SYNC` in your configuration.
 When activated, it automatically handles the configuration of synchronous tool specifications.
 
+**NOTE:** The SYNC server will register only synchronous MCP annotated methods. Asynchronous methods will be ignored.
+
 * **Asynchronous Server** - The asynchronous server implementation uses `McpAsyncServer` and is optimized for non-blocking operations.
 To enable this server type, configure your application with `spring.ai.mcp.server.type=ASYNC`.
 This server type automatically sets up asynchronous tool specifications with built-in Project Reactor support.
 
+**NOTE:** The ASYNC server will register only asynchronous MCP annotated methods. Synchronous methods will be ignored.
+
+
+
 == MCP Server Annotations
 
 The MCP Server Boot Starters provide comprehensive support for annotation-based server development, allowing you to create MCP servers using declarative Java annotations instead of manual configuration.