Update 25.0.0.12-beta-post into draft

posts/2025-09-09-25.0.0.9.adoc

@@ -13,6 +13,8 @@ open-graph-image-alt: Open Liberty Logo
 blog-available-in-languages:
 - lang: zh-Hans
   path: /zh-Hans/blog/2025/09/09/25.0.0.9.html
+- lang: ja
+  path: /ja/blog/2025/09/09/25.0.0.9.html  
 ---
 = ECDH-ES support added to JWT Builder in 25.0.0.9
 Ismath Badsha <https://github.com/IsmathBadsha>

posts/2025-10-23-mcp-standalone-blog.adoc

@@ -32,7 +32,15 @@ Consider a scenario where your company provides weather forecasting services tha
 A more effective solution is to enable the AI to access current weather data through tools exposed by your Liberty application. This allows the AI to retrieve up-to-date forecast information whenever needed, ensuring responses are always based on the most current data available, without the need for AI model retraining.
 
 == How to Use the Liberty MCP Server Feature
-The Liberty MCP Server feature enables a Liberty server to communicate with agentic AI workflows using the MCP protocol with https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http[streamable HTTP]. Using the MCP protocol provides a standardized way for any AI application to be able to discover and utilize the business logic within your application.
+The Liberty MCP Server feature enables a Liberty server to communicate with agentic AI workflows through the MCP protocol. This protocol provides a standardized way for AI applications to discover and utilize the business logic within your application.
+
+The MCP endpoint is available at `/mcp` under your application's context root. For example, if you see this in your logs:
+```
+CWWKT0016I: Web application available (default_host): http://localhost:9080/myMcpApp/
+```
+Then your MCP endpoint can be accessed at `http://localhost:9080/myMcpApp/mcp`. You can connect any MCP client that supports the https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http[Streamable HTTP transport].
+
+To test your MCP server, you can use the https://modelcontextprotocol.io/docs/tools/inspector[MCP Inspector]. With `npm` installed, simply run `npx @modelcontextprotocol/inspector` to download and run it.
 
 === Declaring an MCP Tool
 To expose your business logic to authorized AI applications, you'll need to declare it as an https://modelcontextprotocol.io/specification/2025-06-18/server/tools[MCP tool]. In this context, a tool is a function or operation that the AI can invoke to perform a specific task.