add new page on mcp server for docs

Author: devalog

fern/products/docs/docs.yml

@@ -100,7 +100,12 @@ navigation:
       - page: Conditionally rendered content
         hidden: true
         path: ./pages/component-library/custom-components/conditional-rendering.mdx
-
+  - section: AI features
+    contents:
+      - link: Ask Fern
+        href: /learn/ask-fern/getting-started/what-is-ask-fern
+      - page: MCP server
+        path: ./pages/ai/mcp-server.mdx
   - section: Preview & publish
     collapsed: true
     contents:

fern/products/docs/pages/ai/mcp-server.mdx

@@ -0,0 +1,30 @@
+---
+title: Model Context Protocol
+description: Learn how to use the Model Context Protocol (MCP) to integrate AI capabilities with your Fern documentation
+---
+
+<Tip title="Looking for Fern's own MCP server?">
+ If you want to connect your AI client to Fern's MCP server for help with Ask Fern, Docs, and SDKs, see the [fern-mcp-server repository](https://github.com/fern-api/fern-mcp-server). This page describes how Fern can help you build an MCP server for your own docs site.
+</Tip> 
+
+[Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open standard by Anthropic that enables AI applications to connect with external data sources and tools.
+
+Fern can build a production-ready MCP server for your documentation site. This enables developers using AI assistants (Claude Desktop, Cursor, and Windsurf) to get instant answers about your product directly within their development environment.
+
+## How it works
+
+Fern analyzes your docs site structure and content, then generates an MCP server. AI assistants access your docs through tools like semantic search, endpoint lookup, and code example retrieval. 
+
+This makes your documentation "AI-native" and accessible within the AI tools your developers already use.
+
+<Markdown src="/snippets/wip-callout.mdx" />
+
+## How developers use it 
+
+Developers simply add your MCP server to their AI client configuration. With an MCP server for your docs, developers can ask their AI assistant questions like:
+
+* "How do I authenticate with this API?"
+* "Show me code examples for creating a user"
+* "What are the rate limits for the search endpoint?"
+
+The AI assistant will automatically search your documentation and provide accurate, up-to-date answers with relevant code examples – all without leaving their current tool.