docs: mark Weaviate MCP server GA as of v1.38

The built-in MCP server is generally available as of v1.38 (introduced as a preview in v1.37.1); enable flags are runtime-configurable from v1.38. Replaces the preview admonition with a GA availability note, updates the FAQ wording, and removes the now-unused preview include. Aligns the docs with the 1.38 release announcement (weaviate-io#3636).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: g-despot

_includes/feature-notes/mcp.mdx

@@ -5,7 +5,7 @@ image: og/docs/configuration.jpg
 faq:
   - question: Does Weaviate offer an MCP server?
     answer: >-
-      Yes. Weaviate ships a built-in Model Context Protocol (MCP) server (preview, available from v1.37.1). Enable it with the MCP_SERVER_ENABLED=true environment variable; it runs on the same port as the REST API at /v1/mcp.
+      Yes. Weaviate ships a built-in Model Context Protocol (MCP) server (generally available as of v1.38; introduced in v1.37.1). Enable it with the MCP_SERVER_ENABLED=true environment variable; it runs on the same port as the REST API at /v1/mcp.
   - question: Is the MCP server an external library?
     answer: >-
       No — it's built into the Weaviate Server binary, not a separate package you install. Setting MCP_SERVER_ENABLED=true exposes the MCP endpoint on the same port as the REST API; nothing extra to run or deploy. The separate "Weaviate Docs MCP server" (Kapa-powered, serves documentation to LLMs) is a distinct product.
@@ -22,9 +22,9 @@ faq:
 import Tabs from "@theme/Tabs";
 import TabItem from "@theme/TabItem";
 
-import MCPPreview from "/_includes/feature-notes/mcp.mdx";
-
-<MCPPreview />
+:::info Generally available
+The built-in Weaviate MCP server is generally available as of `v1.38` (introduced as a preview in `v1.37.1`). Its enable flags are runtime-configurable from `v1.38` — see [Environment variables](#environment-variables).
+:::
 
 The Weaviate [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server is an implementation of the open standard that enables Large Language Models (LLMs) to interact securely with your Weaviate instance.