Showing posts with label ai. Show all posts
Showing posts with label ai. Show all posts

Reading Notes #645

Welcome to this week's reading notes! I've found some great articles that caught my eye - from security tips for MCP servers to exciting updates in Rust and AI. Whether you're into cloud services, programming tools, or wondering about the future of coding with AI, there's something here for you.

Let's dive in!

 

Programming

  • The Aspire Compiler (David Fowler) - I really appreciate Aspire. It's one of the tools that completely changed my experience as a developer. Learning more about it is, without a doubt, interesting.

  • Verifying tricky git rebases with git range-diff (Andrew Lock) - Is it possible to really master Git? There is always something new to learn. Nice post going deep.

  • Azure SDK for Rust Goes Beta (Nikos Vaggalis ) - Great news for the Rust developer, this is an important milestone.

AI



Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

If you have interesting content, share it!

~Frank


Making AI smarter with an MCP server that manages short URLs

Have you ever wanted to give your AI assistants access to your own custom tools and data? That's exactly what Model Context Protocol (MCP) allows us to do, and I've been experimenting with it lately.

(Version française ici)

I read a lot recently about Model Context Protocol (MCP) and how it is changing the way AI interacts with external systems. I was curious to see how it works and how I can use it in my own projects. There are many tutorial available online but one of my favorite was written by James Montemagno Build a Model Context Protocol (MCP) server in C#. This post isn't a tutorial, but rather a summary of my experience and what I learned along the way while building a real MCP server that manages short URLs.

MCP doesn't change AI itself, it's a protocol that helps your AI model to interact with external resources: API, databases, etc. The protocol simplifies the way AI can access an external system, and it allows the AI to discover the available tools from those resources. Recently I was working on a project that manages short URLs, and I thought it would be a great opportunity to build an MCP server that manages short URLs. I wanted to see how easy it is to build and then use it in VSCode with GitHub Copilot Chat.

Code: All the code of this post is available in the branch exp/mcp-server of the AzUrlShortener repo on GitHub.

Setting Up: Adding an MCP Server to a .NET Aspire Solution

The AzUrlShortener is a web solution that uses .NET Aspire, so the first thing I did was create a new project using the command:

dotnet new web -n Cloud5mins.ShortenerTools.MCPServer -o ./mcpserver

Required Dependencies

To transform this into an MCP server, I added these essential NuGet packages:

  • Microsoft.Extensions.Hosting
  • ModelContextProtocol.AspNetCore

Since this project is part of a .NET Aspire solution, I also added references to:

  • The ServiceDefaults project (for consistent service configuration)
  • The ShortenerTools.Core project (where the business logic lives)

Integrating with Aspire

Next, I needed to integrate the MCP server into the AppHost project, which defines all services in our solution. Here's how I added it to the existing services:

var manAPI = builder.AddProject<Projects.Cloud5mins_ShortenerTools_Api>("api")
						.WithReference(strTables)
						.WaitFor(strTables)
						.WithEnvironment("CustomDomain",customDomain)
						.WithEnvironment("DefaultRedirectUrl",defaultRedirectUrl);

builder.AddProject<Projects.Cloud5mins_ShortenerTools_TinyBlazorAdmin>("admin")
		.WithExternalHttpEndpoints()
		.WithReference(manAPI);

// 👇👇👇 new code for MCP Server
builder.AddProject<Projects.Cloud5mins_ShortenerTools_MCPServer>("mcp")
		.WithReference(manAPI)
		.WithExternalHttpEndpoints();

Notice how I added the MCP server with a reference to the manAPI - this is crucial as it needs access to the URL management API.

Configuring the MCP Server

To complete the setup, I needed to configure the dependency injection in the program.cs file of the MCPServer project. The key part was specifying the BaseAddress of the httpClient:

var builder = WebApplication.CreateBuilder(args);       
builder.Logging.AddConsole(consoleLogOptions =>
{
    // Configure all logs to go to stderr
    consoleLogOptions.LogToStandardErrorThreshold = LogLevel.Trace;
});
builder.Services.AddMcpServer()
    .WithTools<UrlShortenerTool>();

builder.AddServiceDefaults();

builder.Services.AddHttpClient<UrlManagerClient>(client => 
            {
                client.BaseAddress = new Uri("https+http://api");
            });
            
var app = builder.Build();

app.MapMcp();

app.Run();

That's all that was needed! Thanks to .NET Aspire, integrating the MCP server was straightforward. When you run the solution, the MCP server starts alongside other projects and will be available at http://localhost:{some port}/sse. The /sse part of the endpoint means (Server-Sent Events) and is critical - it's the URL that AI assistants will use to discover available tools.

Implementing the MCP Server Tools

Looking at the code above, two key lines make everything work:

  1. builder.Services.AddMcpServer().WithTools<UrlShortenerTool>(); - registers the MCP server and specifies which tools will be available
  2. app.MapMcp(); - maps the MCP server to the ASP.NET Core pipeline

Defining Tools with Attributes

The UrlShortenerTool class contains all the methods that will be exposed to AI assistants. Let's examine the ListUrl method:

[McpServerTool, Description("Provide a list of all short URLs.")]
public List<ShortUrlEntity> ListUrl()
{
	var urlList = _urlManager.GetUrls().Result.ToList<ShortUrlEntity>();
	return urlList;
}

The [McpServerTool] attribute marks this method as a tool the AI can use. I prefer keeping tool definitions simple, delegating the actual implementation to the UrlManager class that's injected in the constructor: UrlShortenerTool(UrlManagerClient urlManager).

The URL Manager Client

The UrlManagerClient follows standard HttpClient patterns. It receives the pre-configured httpClient in its constructor and uses it to communicate with the API:

public class UrlManagerClient(HttpClient httpClient)
{
	public async Task<IQueryable<ShortUrlEntity>?> GetUrls()
    {
		IQueryable<ShortUrlEntity> urlList = null;
		try{
			using var response = await httpClient.GetAsync("/api/UrlList");
			if(response.IsSuccessStatusCode){
				var urls = await response.Content.ReadFromJsonAsync<ListResponse>();
				urlList = urls!.UrlList.AsQueryable<ShortUrlEntity>();
			}
		}
		catch(Exception ex){
			Console.WriteLine(ex.Message);
		}
        
		return urlList;
    }

	// other methods to manage short URLs
}

This separation of concerns keeps the code clean - tools handle the MCP interface, while the client handles the API communication.

Using the MCP Server with GitHub Copilot Chat

Now for the exciting part - connecting your MCP server to GitHub Copilot Chat! This is where you'll see your custom tools in action.

Configuring Copilot to Use Your MCP Server

Once the server is running (either deployed in Azure or locally), follow these steps:

  1. Open GitHub Copilot Chat in VS Code
  2. Change the mode to Agent by clicking the dropdown in the chat panel
  3. Click the Select Tools... button, then Add More Tools
Set GitHub Copilot mode to Agent

Selecting the Connection Type

GitHub Copilot supports several ways to connect to MCP servers:

All MCP Server types

There are multiple options available - you could have your server in a container or run it via command line. For our scenario, we'll use HTTP.

Note: At the time of writing this post, I needed to use the HTTP URL of the MCP server rather than HTTPS. You can get this URL from the Aspire dashboard by clicking on the resource and checking the available Endpoints.

After selecting your connection type, Copilot will display the configuration file, which you can modify anytime.

GitHub Copilot Chat Configuration

Interacting with Your Custom Tools

Now comes the fun part! You can interact with your MCP server in two ways:

  1. Natural language queries: Ask questions like "How many short URLs do I have?"
  2. Direct tool references: Use the pound sign to call specific tools: "With #azShortURL list all URLs"

The azShortURL is the name we gave to our MCP server in the configuration.

GitHub Copilot question and response example


Key Learnings and Future Directions

Building this MCP server for AzUrlShortener taught me several valuable lessons:

What Worked Well

  • Integration with .NET Aspire was remarkably straightforward
  • The attribute-based approach to defining tools is clean and intuitive
  • The separation of tool definitions from implementation logic keeps the code maintainable

Challenges and Considerations

  • The csharp-SDK is only a few weeks old and still in preview
  • OAuth authentication isn't defined yet (though it's being actively worked on)
  • Documentation is present but evolving rapidly as the technology matures, so some features may not be fully documented yet

For the AzUrlShortener project specifically, I'm keeping this MCP server implementation in the experimental branch mcp-server until I can properly secure it. However, I'm already envisioning numerous other scenarios where MCP servers could add great value.

If you're interested in exploring this technology, I encourage you to:

  • Check out the GitHub repo
  • Fork it and create your own MCP server
  • Experiment with different tools and capabilities

Join the Community

If you have questions or want to share your experiences with others, I invite you to join the Azure AI Community Discord server:

Join Azure AI Community Discord

The MCP ecosystem is growing rapidly, and it's an exciting time to be part of this community!


~Frank


Reading Notes #644

This post gathers my recent reading notes on artificial intelligence, programming, and a few inspiring podcasts. It includes links to articles, tutorials, and fascinating discussions. Whether you're interested in the latest AI developments, .NET tools, or modern architectures, there's plenty here to spark your curiosity. 


Happy reading!

AI


Programming


Podcasts

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

If you have interesting content, share it!

~Frank

Reading Notes #643

In this week Reading Notes, we explore a diverse range of updates and insights from the tech world. From the latest features in the Azure SDK and Developer CLI, to an introduction to .NET Aspire and its innovative approach to Infrastructure as Code, there's plenty to catch up on. 

Jump into discussions on AI productivity, free Azure SQL tiers, and even a refreshing podcast on stress-free living. 


Let's get started!


Cloud

Databases

AI

Programming

Podcasts


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 


If you have interesting content, share it!

~Frank

Reading Notes #642

This week, I explored posts about improving cache management for ASP.NET Core applications and understanding error handling in Blazor. These articles, along with others on AI model selection and development productivity, offer valuable insights for developers.


Cloud


Programming


AI


Miscellaneous



Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 


If you have interesting content, share it!

~Frank

Reading Notes #641

This week's reading notes cover an array of topics, from programming insights and AI advancements to cloud solutions and practical tips for developers. Explore the updates, tools, and advice that could inspire your next project!
web dev in a D&D monsters card style
prompt: Web dev in a D&D monsters card style


 

Suggestion of the week


Cloud


Programming


AI


Miscellaneous


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 


If you have interesting content, share it!

~Frank

Reading Notes #640

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

If you have interesting content, share it! 

Cloud


AI


Programming

~frank

Reading Notes #639

Welcome to Reading Notes #639, a curated selection of intriguing articles across programming, AI, cloud computing, and more. Dive into new productivity features in Visual Studio, the latest front-end development trends, .NET AI evaluations, and essential learning techniques. 

Grab your coffee and enjoy the read!


Cloud

Programming

AI

Miscellaneous


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

If you have interesting content, share it! 

~frank

Reading Notes #638

Welcome to Reading Notes —a curated dive into the latest and greatest in programming, cloud, and AI. From mastering multithreading with Azure to exploring GitHub Copilot's productivity potential, this collection is brimming with knowledge. Let's unravel what's new, innovative, and worth your attention!


Cloud


Programming

AI

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

If you have interesting content, share it! 

~frank


Reading Notes #636

Welcome back to another edition of my Reading Notes! This week, we've got some great content lined up, including insights on cloud development with Azure Developer CLI, tips for promoting your open source projects, updates on .NET, and more. Dive in to explore a wealth of knowledge and stay updated with the latest trends and developments.

Cloud

Programming

AI

Miscellaneous


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

 If you have interesting content, share

~Frank


Reading Notes #634

Each week, I read a myriad of topics that pique my curiosity and spark new ideas. From AI advancements and low-code solutions to tutorials on enhancing accessibility and performing database operations in .NET MAUI, this week's reading notes offer an eclectic mix of insights and practical knowledge. 

Dive in and explore the fascinating links that kept me captivated over the past few days! 


AI

Programming

Miscellaneous

  • Using Tools (Safely) with LLMs (Mark Heath) - This is a nice C# tutorial that explains how to extend the capabilities of your AI without compromising security.

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share 

~frank

Reading Notes #633

This edition of Readings Notes covers the synergies between C# and Rust, open-source software licensing challenges, and securing the software supply chain. It also feature a beginner’s guide to programming C# in Visual Studio Code. Finally, we delve into the evaluation process of AI models for GitHub Copilot. 

Enjoy the read!

man looking at the camera with a frozen lake behind him
Programming

Miscellaneous

  • How we evaluate AI models and LLMs for GitHub Copilot (Connor Adams, Klint Finley) - This is an interesting post that shares the methods used to test the different models before they can be included. Testing a model is different than testing a regular piece of code, what are they looking for, and what's important?
Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share 

~frank

Reading Notes #632


In this edition of ReadingNotes, we explore some fascinating topics in the world of cloud computing, programming, and AI. From integrating images with AI in C# to the latest updates in Git, there's something for everyone. Plus, don't miss out on insights into effective developer relations and a deep dive into a new AI agent for Docker. 

Enjoy the read!

Cloud

Programming

  • Highlights from Git 2.48 (Taylor Blau) - A nice update with many new features and bug fixes. There are 93 contributors to this update. It's pretty impressive.

AI

  • Meet Gordon: An AI Agent for Docker (Christopher Petito) - Oh! I like those specialized AI! One thing that could be nice is Docker could make accessible an Ask Gordon plugin that other AI like Copilot could use.

Miscellaneous

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share 

~frank

Reading Notes #631

Welcome to this week's roundup! I'm excited to share some standout blog posts and podcasts that caught my attention. Enjoy exploring the latest updates, tips, and insights!

Suggestion of the week

  • azd CDN changing January 2025 (Kristen Womack) - Important note, that will probably impact many of you, like I was. Luckily the fix is very simple

Programming

AI

  • AI Killed the Content Creator...Star 🤩 (Kirupa) - Interesting observation. The artificial intelligence is impacting all processes and changes the way we interact with the world. Will I kill it or change it?

Podcasts

  • 438: Jon Galloway - From Submarine Office to Software Developer (Merge Conflict) - Super interesting episode about Jon. I learn more in those minutes than in all the time I've been working with him! But at the same time, a Teams call is not "the place" to share about Submarine stuff I guess ;)

  • .NET Aspire with Anthony Simmon (Hanselminutes) - Interesting episode about .NET Aspire by someone who is using it in his day to day and have been extending it. Great conversation, very interesting.

Miscellaneous


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share 

~frank


Reading Notes #627


This week, I stumbled upon some fascinating reads. From the announcement of .NET 9 and its incredible versatility to an intriguing new type of failover for Azure Storage, there's plenty to explore. Discover how to get .NET 9 running on your Raspberry Pi, check out the latest Blazorise update, and delve into the power of GitHub Models in .NET with Semantic Kernel. Plus, don't miss out on the introduction of GitHub Copilot for Azure and a new season of AI-related sessions in Visual Studio. And for my fellow open-source enthusiasts, the .NET Aspire Community Toolkit is a game-changer. 

Dive in and let's geek out together! 🌟

Suggestion of the week

  • Announcing .NET 9 - .NET Blog (.NET Team) - You can build anything with C# (aka .NET) and I love it! With runs everywhere, it's open source, it's fast and free!

Cloud

Programming

  • Install and use Microsoft Dot NET 9 with the Raspberry Pi (Pete Codes) - C# everywhere! I love it! I do have some code that run on a Pi as a mini server, bubi need to have a look for a IoT library that could be used.

  • Blazorise v1.7 (Mladen Macanović) - New version of a nice looking CSS Framework for our Blazor website with more features and better performance.

AI

Data

Open Source

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.
If you have interesting content, share it!


~ Frank


Reading Notes #625

Welcome to another edition of Reading Notes! This week, dive into the latest updates on Azure DevOps, Docker best practices, System.Text.Json enhancements in .NET 9, AI innovations from GitHub Universe, and more. 

Enjoy your reading!

Cloud

Programming

AI

  • GitHub Spark (Devon Rifkin, Terkel Gjervig Nielsen, Cole Bemis, Alice Li) - Fascinating news from GitHub Universe. A new spin on the lowcode app but with code. Looking forward to trying it and see what I can build with it.

  • GitHub Copilot in Windows Terminal (Christopher Nguyen) - There it is, Copilot making his entrance into our beloved Terminal. It's only in version Canary for now, but I'm sure it will help many of us when no sure what command to use, or the equivalent bash/ PowerShell.

Miscellaneous


Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share it!


~ Frank


Reading Notes #624

Dive into this week's fascinating mix of tech insights, troubleshooting tales, and productivity tips. From the latest in Azure Dev tools to real-world debugging adventures and cutting-edge .NET innovations, there's something for everyone.

Happy reading!

Cloud

Programming

Podcast

  • Microsoft Playwright Testing with Debbie O'Brien (.NET Rocks!) - Great tool to help making tests on our websites. It's open source and now support .NET.

  • Inspektor Gadget (DevOps and Docker Talk: Cloud Native Interviews and Tooling) - THe first time I heard about Inspektor Gadget was in an episode of Open at Microsoft. I don't use much Kubernetes, but that will be part of my toolbox when I do. Great security, troubleshooting, and observability utility.

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share it!


~ Frank


Reading Notes #623

Ready for another round of intriguing reads and insightful listens? This week's edition of Reading Notes dives into the seamless blending of Python and .NET, fresh monetisation strategies in open source, AI innovations, and thought-provoking podcast discussions. 

Get comfy and let's dive in!

path in a forest surround by large trees



Programming

AI

Podcast

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

If you have interesting content, share it!

~ Frank

Reading Notes #620

It's Reading Notes time and this week we learn how to improve our experience and security while using AI and containers
 a zip line spider?

Sharing my Reading Notes is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week.

Cloud

AI

Programming

~Frank

Reading Notes #619

It's reading notes time! It is a habit I started a long time ago, where I share a list of all the articles, blog posts, and books that catch my interest during the week. 

You also read something you liked? Share it!

Suggestion of the week

Programming

~Frank