Merge pull request #1988 from jasonrandrews/review

Review MCP server on R Pi 5 Learning Path

Author: jasonrandrews

content/learning-paths/cross-platform/mcp-ai-agent/_index.md

@@ -1,8 +1,6 @@
 ---
 title: Deploy an MCP Server on Raspberry Pi 5 for AI Agent Interaction using OpenAI SDK
 
-
-    
 minutes_to_complete: 30
 
 who_is_this_for: This Learning Path is for LLM and IoT developers who want to run and interact with AI agents on edge devices like the Raspberry Pi 5. You'll learn how to deploy a lightweight Model Context Protocol (MCP) server and use the OpenAI Agent SDK to create and register tools for intelligent local inference.
@@ -24,11 +22,11 @@ author: Andrew Choi
 skilllevels: Introductory
 subjects: ML
 armips:
-    - Cortex-A76
+    - Cortex-A
 tools_software_languages:
     - Python
-    - IoT
     - AI
+    - Raspberry Pi
     - MCP
 
 operatingsystems:

content/learning-paths/cross-platform/mcp-ai-agent/intro-to-mcp-uv.md

@@ -31,7 +31,7 @@ Some key features:
 For further information on `uv`, see: [https://github.com/astral-sh/uv](https://github.com/astral-sh/uv).
 
 
-### A high-level view of the architecture
+## A high-level view of the architecture
 
  ![Diagram of Model Context Protocol (MCP) architecture showing the interaction between MCP Host (LLM-powered app), MCP Client (runtime shim), and MCP Server, which connects to local data sources (files, sensors, databases) and remote APIs for AI agent context retrieval.](./mcp.png)
 
@@ -49,7 +49,7 @@ Each component in the diagram plays a distinct role in enabling AI agents to int
 Learn more about AI Agents in the Learning Path [Deploy an AI Agent on Arm with llama.cpp and llama-cpp-agent using KleidiAI](https://learn.arm.com/learning-paths/servers-and-cloud-computing/ai-agent-on-cpu/).
 {{% /notice %}}
 
-### Section summary
+## Section summary
 
 This page introduces MCP and `uv` as foundational tools for building fast, secure, and modular AI agents that run efficiently on edge devices like the Raspberry Pi 5.
 

content/learning-paths/cross-platform/mcp-ai-agent/mcp-client.md

@@ -10,7 +10,8 @@ In this section, you'll learn how to set up an AI Agent on your development mach
 
 These commands were tested on a Linux Arm development machine. 
 
-### Create an AI Agent and point it at your Pi's MCP Server
+## Create an AI Agent and point it at your Pi's MCP Server
+
 1. Install `uv` on your development machine:
 
 ```bash
@@ -41,7 +42,7 @@ uv add openai-agents python-dotenv
 echo -n "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" > .env
 ```
 
-### Write the Python script for the Agent Client
+## Write the Python script for the Agent Client
 
 Use a file editor of your choice and replace the content of the sample `main.py` with the content shown below:
 
@@ -88,7 +89,7 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-### Execute the Agent
+## Execute the Agent
 
 You’re now ready to run the AI Agent and test its connection to your running MCP server on the Raspberry Pi 5.
 
@@ -111,7 +112,8 @@ Congratulations! Your local AI Agent just called the MCP server on your Raspberr
 
 This lightweight protocol isn’t just a game-changer for LLM developers—it also empowers IoT engineers to transform real-world data streams and give AI direct, reliable control over any connected device.
 
-### Next Steps
+## Next Steps
+
 - **Expand Your Toolset**  
    - Write additional `@mcp.tool()` functions for Pi peripherals (such as GPIO pins, camera, and I²C sensors).  
    - Combine multiple MCP servers (for example, filesystem, web-scraper, and vector-store memory) for richer context.  
@@ -120,6 +122,7 @@ This lightweight protocol isn’t just a game-changer for LLM developers—it al
    - Hook into Home Assistant or Node-RED through MCP.  
    - Trigger real-world actions (for example, turn on LEDs, read environmental sensors, and control relays).  
 
-   ### Section summary
+## Section summary
+
 You’ve now built and run an AI agent on your development machine that connects to an MCP server on your Raspberry Pi 5. Your agent can now interact with real-world data sources in real time — a complete edge-to-cloud loop powered by OpenAI’s Agent SDK and the MCP protocol.
 

content/learning-paths/cross-platform/mcp-ai-agent/mcp-server.md

@@ -138,7 +138,7 @@ ngrok http 8000
 ```
 4. Copy the generated HTTPS URL (e.g. `https://abcd1234.ngrok-free.app`). You’ll use this endpoint to connect external tools or agents to your MCP server. Keep this URL available for the next steps in your workflow.
 
-### Section summary
+## Section summary
 
 You now have a working FastMCP server on your Raspberry Pi 5. It includes tools for reading CPU temperature and retrieving weather data, and it's accessible over the internet via a public HTTPS endpoint using ngrok. This sets the stage for integration with LLM agents or other external tools.