splitting up into dedicated chapters

Author: Chris

05-AdvancedTopics/README.md

@@ -1,12 +1,15 @@
 # Advanced Topics in MCP 
 
+This chapter is meant to cover a series of advanced topics in Model Context Protocol (MCP) implementation, including multi-modal integration, scalability, security best practices, and enterprise integration. These topics are crucial for building robust and production-ready MCP applications that can meet the demands of modern AI systems.
+
 ## Overview
 
 This lesson explores advanced concepts in Model Context Protocol implementation, focusing on multi-modal integration, scalability, security best practices, and enterprise integration. These topics are essential for building production-grade MCP applications that can handle complex requirements in enterprise environments.
 
 ## Learning Objectives
 
 By the end of this lesson, you will be able to:
+
 - Implement multi-modal capabilities within MCP frameworks
 - Design scalable MCP architectures for high-demand scenarios
 - Apply security best practices aligned with MCP's security principles
@@ -17,15 +20,15 @@ By the end of this lesson, you will be able to:
 
 | Link | Title | Description |
 |------|-------|-------------|
-| [MCP OAuth2 sample](./mcp-oauth2-demo/) | MCP OAuth2 Demo | Minimal Spring Boot app showing OAuth2 with MCP, both as Authorization and Resource Server. Demonstrates secure token issuance, protected endpoints, Azure Container Apps deployment, and API Management integration. |
-| [Web Search sample](./web-search-mcp/) | Web Search MCP | Python MCP server and client integrating with SerpAPI for real-time web, news, product search, and Q&A. Demonstrates multi-tool orchestration, external API integration, and robust error handling. |
-| [Multi modal sample](./mcp-multi-modality/README.md) | MCP Multi modal samples  | Samples for audio, image and multi modal response |
-| [Integration with Azure](./mcp-integration/README.md) | Integrate with Azure | Learn how to integrate your MCP Server on Azure |
-| [Root Contexts](./mcp-root-contexts/README.md) | Root contexts  | Learn more about root context and how to implement them |
-| [Routing](./mcp-routing/README.md) | Routing | Learn different types of routing |
-| [Sampling](./mcp-sampling/README.md) | Sampling | Learn how to work with sampling |
-| [Scaling](./mcp-scaling/README.md) | Scaling  | Learn about scaling |
-| [Security](./mcp-security/README.md) | Security  | Secure your MCP Server |
+| [5.1 Integration with Azure](./mcp-integration/README.md) | Integrate with Azure | Learn how to integrate your MCP Server on Azure |
+| [5.2 Multi modal sample](./mcp-multi-modality/README.md) | MCP Multi modal samples  | Samples for audio, image and multi modal response |
+| [5.3 MCP OAuth2 sample](./mcp-oauth2-demo/) | MCP OAuth2 Demo | Minimal Spring Boot app showing OAuth2 with MCP, both as Authorization and Resource Server. Demonstrates secure token issuance, protected endpoints, Azure Container Apps deployment, and API Management integration. |
+| [5.4 Root Contexts](./mcp-root-contexts/README.md) | Root contexts  | Learn more about root context and how to implement them |
+| [5.5 Routing](./mcp-routing/README.md) | Routing | Learn different types of routing |
+| [5.6 Sampling](./mcp-sampling/README.md) | Sampling | Learn how to work with sampling |
+| [5.7 Scaling](./mcp-scaling/README.md) | Scaling  | Learn about scaling |
+| [5.8 Security](./mcp-security/README.md) | Security  | Secure your MCP Server |
+| [5.9 Web Search sample](./web-search-mcp/README.md) | Web Search MCP | Python MCP server and client integrating with SerpAPI for real-time web, news, product search, and Q&A. Demonstrates multi-tool orchestration, external API integration, and robust error handling. |
 
 ## Additional References
 
@@ -61,4 +64,4 @@ Design an enterprise-grade MCP implementation for a specific use case:
 
 ## What's next
 
-- [5.1 MCP OAuth2 Demo](./mcp-oauth2-demo/README.md)
+- [5.1 MCP Integration](./mcp-integration/README.md)

05-AdvancedTopics/mcp-integration/README.md

@@ -1,8 +1,28 @@
-## Enterprise Integration
+# Enterprise Integration
 
-Integrating MCP with enterprise systems like Azure OpenAI and Microsoft AI Foundry.
+When building MCP Servers in an enterprise context, you often need to integrate with existing AI platforms and services. This section covers how to integrate MCP with enterprise systems like Azure OpenAI and Microsoft AI Foundry, enabling advanced AI capabilities and tool orchestration.
 
-### Azure OpenAI Integration
+## Introduction
+
+In this lesson, you'll learn how to integrate Model Context Protocol (MCP) with enterprise AI systems, focusing on Azure OpenAI and Microsoft AI Foundry. These integrations allow you to leverage powerful AI models and tools while maintaining the flexibility and extensibility of MCP.
+
+## Learning Objectives
+
+By the end of this lesson, you will be able to:
+
+- Integrate MCP with Azure OpenAI to utilize its AI capabilities.
+- Implement MCP tool orchestration with Azure OpenAI.
+- Combine MCP with Microsoft AI Foundry for advanced AI agent capabilities.
+- Leverage Azure Machine Learning (ML) for executing ML pipelines and registering models as MCP tools.
+
+## Azure OpenAI Integration
+
+Azure OpenAI provides access to powerful AI models like GPT-4 and others. Integrating MCP with Azure OpenAI allows you to utilize these models while maintaining the flexibility of MCP's tool orchestration.
+
+<details>
+<summary>csharp</summary>
+
+In this code snippet, we demonstrate how to integrate MCP with Azure OpenAI using the Azure OpenAI SDK. 
 
 ```csharp
 // .NET Azure OpenAI Integration
@@ -66,7 +86,24 @@ namespace EnterpriseIntegration
 }
 ```
 
-### Microsoft AI Foundry Integration
+In the preceding code we've:
+
+- Configured the Azure OpenAI client with the endpoint, deployment name and API key.
+- Created a method `GetCompletionWithToolsAsync` to get completions with tool support.
+- Handled tool calls in the response.
+
+You're encouraged to implement the actual tool handling logic based on your specific MCP server setup.
+
+</details>
+
+## Microsoft AI Foundry Integration
+
+Azure AI Foundry provides a platform for building and deploying AI agents. Integrating MCP with AI Foundry allows you to leverage its capabilities while maintaining the flexibility of MCP.
+
+In the below code, we develop an Agent integration that processes requests and handles tool calls using MCP.
+
+<details>
+<summary>Java</summary>
 
 ```java
 // Java AI Foundry Agent Integration
@@ -124,7 +161,20 @@ public class AIFoundryMcpBridge {
 }
 ```
 
-### Python Enterprise Integration Example
+In the preceding code, we've:
+
+- Created an `AIFoundryMcpBridge` class that integrates with both AI Foundry and MCP.
+- Implemented a method `processAgentRequest` that processes an AI Foundry agent request.
+- Handled tool calls by executing them through the MCP client and submitting the results back to the AI Foundry agent.
+
+</details>
+
+## Integrating MCP with Azure ML
+
+Integrating MCP with Azure Machine Learning (ML) allows you to leverage Azure's powerful ML capabilities while maintaining the flexibility of MCP. This integration can be used to execute ML pipelines, register models as tools, and manage compute resources.
+
+<details>
+<summary>Python</summary>
 
 ```python
 # Python Azure AI Integration
@@ -247,3 +297,17 @@ class EnterpriseAiIntegration:
         }
         return mapping.get(ml_type, "string")
 ```
+
+In the preceding code, we've:
+
+- Created an `EnterpriseAiIntegration` class that integrates MCP with Azure ML.
+- Implemented an `execute_ml_pipeline` method that processes input data using MCP tools and submits an ML pipeline to Azure ML.
+- Implemented a `register_ml_model_as_tool` method that registers an Azure ML model as an MCP tool, including creating the necessary deployment environment and compute resources.
+- Mapped Azure ML data types to JSON schema types for tool registration.
+- Used asynchronous programming to handle potentially long-running operations like ML pipeline execution and model registration.
+
+</details>
+
+## What's next
+
+- [Multi modality](../mcp-multi-modality/README.md)

05-AdvancedTopics/mcp-multi-modality/README.md

@@ -1,8 +1,8 @@
 # Multi-Modal Integration
 
-MCP supports not just text-based interactions but also multi-modal capabilities, allowing models to work with images, audio, and other data types.
+Multi-modal applications are becoming increasingly important in AI, enabling richer interactions and more complex tasks. The Model Context Protocol (MCP) provides a framework for building multi-modal applications that can handle various types of data, such as text, images, and audio.
 
-This chapter demonstrates how to build a real-world multi modal application.
+MCP supports not just text-based interactions but also multi-modal capabilities, allowing models to work with images, audio, and other data types.
 
 ## Introduction
 
@@ -19,12 +19,12 @@ By the end of this lesson, you will be able to:
 
 Multi-modal MCP implementations typically involve:
 
-- **Modal-Specific Parsers**: Components that convert different media types into formats the model can process
+- **Modal-Specific Parsers**: Components that convert different media types into formats the model can process.
 - **Modal-Specific Tools**: Special tools designed to handle specific modalities (image analysis, audio processing)
 - **Unified Context Management**: System to maintain context across different modalities
-- **Response Generation**: Capability to generate responses that may include multiple modalities
+- **Response Generation**: Capability to generate responses that may include multiple modalities.
 
-### Multi-Modal Example: Image Analysis
+## Multi-Modal Example: Image Analysis
 
 In the below example, we will analyze an image and extract information.
 
@@ -161,13 +161,25 @@ namespace MultiModalMcpExample
 }
 ```
 
+In the preceding example, we've:
+
+- Created an `ImageAnalysisTool` that can analyze images using a hypothetical `IImageAnalysisService`.
+- Configured the MCP server to handle larger requests and support image content types.
+- Registered the image analysis tool with the server.
+- Implemented a method to download images from a URL and analyze them based on the requested type (objects, text, faces, etc.).
+- Returned structured results in a format compliant with the MCP specification.
+
 </details>
 
-### Multi-Modal Example: Audio Processing
+## Multi-Modal Example: Audio Processing
+
+Audio processing is another common modality in multi-modal applications. Below is an example of how to implement an audio transcription tool that can handle audio files and return transcriptions.
 
 <details>
 <summary>Java</summary>
 
+Let's implement an audio transcription tool:
+
 ```java
 package com.example.mcp.multimodal;
 
@@ -294,6 +306,17 @@ public class MultiModalApplication {
 }
 ```
 
+In the preceding example, we've:
+
+- Created an `AudioTranscriptionTool` that can transcribe audio files. 
+- Defined the tool's schema to accept either a URL or base64-encoded audio data.
+- Implemented the `execute` method to handle audio processing and transcription.
+- Configured the MCP server to handle multi-modal requests, including audio and image processing.
+- Registered the audio transcription tool with the server.
+- Implemented a method to download audio files from a URL or decode base64 audio data.
+- Used an `AudioProcessor` service to handle the actual transcription logic.
+- Started the MCP server to listen for requests.
+
 </details>
 
 ### Multi-Modal Example: Multi-Modal Response Generation
@@ -449,3 +472,7 @@ if __name__ == "__main__":
 ```
 
 </details>
+
+## What's next
+
+- [Oauth 2](../mcp-oauth2-demo/README.md)

05-AdvancedTopics/mcp-oauth2-demo/README.md

@@ -113,4 +113,4 @@ APIM will fetch the JWKS and validate every request.
 
 ## What's next
 
-- [5.2 Web Search MCP Sample](../web-search-mcp/README.md)
+- [Root contexts](../mcp-root-contexts/README.md)