Stop Writing Git Commits: How AI-Powered GitKraken CLI Accelerates Your Development

As developers, we're constantly looking for tools that can help us stay in the flow and be more productive. Today, I want to share a powerful tool that's been gaining traction in the developer community: GitKraken CLI. This command-line interface brings together several key features that modern developers love - it's AI-powered, terminal-based, and incredibly efficient for managing Git workflows.

(Version française ici)

What Makes GitKraken CLI Special?

GitKraken CLI (accessible via the gk command) stands out because it simplifies complex Git workflows while adding intelligent automation. Unlike traditional Git commands, it provides a more intuitive workflow management system that can handle multiple repositories simultaneously.

Getting Started

Installation is straightforward. On Windows, you can install it using:

winget install gitkraken.cli

Once installed, you'll have access to the gk command, which becomes your gateway to streamlined Git operations.

The Workflow in Action

Let's walk through a typical development session using GitKraken CLI:

1. Starting a Work Session

Instead of manually creating branches and switching contexts, you can start a focused work session:

gk w start "Add Behind my Cloud feed" -i "Add Behind my Cloud feed #1"

This single command:

• Creates a new branch based on your issue/feature name
• Switches to that branch automatically
• Links the work session to a specific issue
• Sets up your development environment for focused work

2. Managing Multiple Work Sessions

You can easily see all your active work sessions:

gk w list

This is particularly powerful when working across multiple repositories or juggling several features simultaneously.

3. Committing with Intelligence

After making your changes, adding files works as expected:

gk add .

But here's where the AI magic happens. Instead of writing commit messages manually:

gk w commit --ai

The AI analyzes your changes and generates meaningful, descriptive commit messages automatically. No more "quick fix" or "update stuff" commits!

4. Pushing and Creating Pull Requests

Publishing your work is equally streamlined:

gk w push

And when you're ready to create a pull request:

gk w pr create --ai

Again, AI assistance helps generate appropriate PR titles and descriptions based on your work.

5. Wrapping Up

Once your work is complete and merged, clean up is simple:

gk w end

This command:

• Switches you back to the main branch
• Deletes the feature branch, locally and on GitHub
• Closes the work session
• Leaves your repository clean and ready for the next task

Why This Matters

The beauty of GitKraken CLI lies in its ability to keep you in the zone. You don't need to:

• Switch between multiple tools
• Remember complex Git commands
• Write commit messages from scratch
• Manually manage branch lifecycle

Everything flows naturally from one command to the next, maintaining your focus on what matters most: writing code.

Multi-Repository Power

One of the standout features is GitKraken CLI's ability to manage multiple repositories simultaneously. This is invaluable for:

• Microservices architectures
• Full-stack applications with separate frontend/backend repos
• Organizations with multiple related projects

Try It Yourself

GitKraken CLI is part of a broader suite of developer tools that GitKraken offers. The CLI itself is free to use, which makes it easy to experiment with and integrate into your workflow without any upfront commitment. If you find value in the CLI and want to explore their other tools, GitKraken has various products that might complement your development setup.

The learning curve is genuinely minimal since it builds on Git concepts you already know while adding helpful automation. I've found that even small workflow improvements can compound over time, especially when you're working on multiple projects or dealing with frequent context switching.

If you're curious about what else GitKraken offers beyond the CLI, you can explore their full product lineup here. For those who decide the Pro features would benefit their workflow, as an ambassador of GitKraken I can share my code to provide a 50% discount for your GitKraken Pro subscription.

The combination of AI assistance and intuitive commands addresses real pain points that many developers face daily. Whether GitKraken CLI becomes a core part of your toolkit will depend on your specific workflow, but it's worth trying given that it's free and takes just a few minutes to set up.

---

The best tools are the ones that get out of your way and let you focus on building. GitKraken CLI aims to do exactly that.

Reading Notes #652

This week, we explore a variety of topics, from database containerization and AI security risks to the evolving landscape of gaming devices and cloud technologies. We also explore the shift towards security-first development and the integration of .NET Aspire with SQL Server for integration testing.

Let's dive in!

Suggestion of the week

• GitHub MCP Exploited: Accessing private repositories via MCP (Marco Milanta, Luca Beurer-Kellner) - AI tools are very powerful but also pretty new in our lives. It's important to stay up to date and understand the risks. Not scared, but to see the potential flaws and how to avoid them.

Cloud

• Azure Container Apps vs AKS: Which Is Right for Your Enterprise Application? (Chris Pietschmann) - This post answers a common question about those two services.

Programming

• Beyond DevSecOps: The Rise of Security-First Development (Industry Perspectives) - DevSecOps was a wake-up call, and we need to build our app security first. That seems to make sense, right? Have a read of this post to dig deeper into this idea and understand its foundation

• .NET Aspire dev-time orchestration for SQL Server integration tests (Ian Griffiths) - First post of a series about the spire and database, this one just set the initial setup. Stay tuned for more

Databases

• Running a MySQL database in a Docker Container (Mercy Bassey) - Running databases in a container is a real game changer for developers.

Miscellaneous

• SteamOS puts the pressure on Microsoft’s Xbox-branded handheld (Tom Warren) - Gaming devices are in a completely different world, and, normally, all OS need to adapt. A fascinating post about steamOS and the future of Windows in that scope

~frank

I Co-Wrote 88 Unit Tests Using AI: A Developer's Journey

Testing has always been one of those tasks that developers know is essential but often find tedious. When I decided to add comprehensive unit tests to my NoteBookmark project, I thought: why not make this an experiment in AI-assisted development? What followed was a fascinating 4-hour journey that resulted in 88 unit tests, a complete CI/CD pipeline, and some valuable insights about working with AI coding assistants.

(Version française ici)

The Project: NoteBookmark

NoteBookmark is a .NET application built with C# that helps users manage and organize their reading notes and bookmarks. The project includes an API, a Blazor frontend, and uses Azure services for storage. You can check out the complete project on GitHub.

The Challenge: Starting from Zero

I'll be honest - it had been a while since I'd written comprehensive unit tests. Rather than diving in myself, I decided to see how different AI models would approach this task. My initial request was deliberately vague: "add a test project" without any other specifications.

Looking back, I realize I should have been more specific about which parts of the code I wanted covered. This would have made the review process easier and given me better control over the scope. But sometimes, the best learning comes from letting the AI surprise you.

The Great AI Model Comparison

GPT-4.1: Competent but Quiet

GPT-4.1 delivered decent results, but the experience felt somewhat mechanical. The code it generated was functional, but I found myself wanting more context. The explanations were minimal, and I often had to ask follow-up questions to understand the reasoning behind certain test approaches.

Gemini: The False Start

My experience with Gemini was... strange. Perhaps it was a glitch or an off day, but most of what was generated simply didn't work. I didn't persist with this model for long, as debugging AI-generated code that fundamentally doesn't function defeats the purpose of the exercise. Note that at the time of this writing, Gemini was still in preview, so I expect it to improve over time.

Claude Sonnet: The Clear Winner

This is where the magic happened. Claude Sonnet became my co-pilot of choice for this project. What set it apart wasn't just the quality of the code (though that was excellent), but the quality of the conversation. It felt like having a thoughtful colleague thinking out loud with me.

The explanations were clear and educational. When Claude suggested a particular testing approach, it would explain why. When it encountered a complex scenario, it would walk through its reasoning. I tried different versions of Claude Sonnet but didn't notice significant differences in results - they were all consistently good.

The Development Process: A 4-Hour Journey

Hour 1-2: Getting to Compilation

The first iteration couldn't compile. This wasn't surprising given the complexity of the codebase and the vague initial request. But here's where the AI collaboration really shined. Instead of manually debugging everything myself, I worked with Copilot to identify and fix issues iteratively.

We went through several rounds of:

1. Identify compilation errors
2. Discuss the best approach to fix them
3. Let the AI implement the fixes
4. Review and refine

After about 2 hours, we had a test project with 88 unit tests that compiled successfully. The AI had chosen xUnit as the testing framework, which I was happy with - it's a solid choice that I might not have picked myself if I was rusty on the current .NET testing landscape.

Hour 2.5-3.5: Making Tests Pass

Getting the tests to compile was one thing; getting them to pass was another challenge entirely. This phase taught me a lot about both my codebase and xUnit features I wasn't familiar with.

I relied heavily on the /explain feature during this phase. When tests failed, I'd ask Claude to explain what was happening and why. This was invaluable for understanding not just the immediate fix, but the underlying testing concepts.

One of those moment was learning about [InlineData(true)] and other xUnit data attributes. These weren't features I was familiar with, and having them explained in context made them immediately useful.

Hour 3.5-4: Structure and Style

Once all tests were passing, I spent time ensuring I understood each test and requesting structural changes to match my preferences. This phase was crucial for taking ownership of the code. Just because AI wrote it doesn't mean it should remain a black box. Let's repeat this: Understanding the code is essential; just because AI wrote it doesn't mean it's good.

Beyond Testing: CI/CD Integration

With the tests complete, I asked Copilot to create a GitHub Actions workflow to run tests on every push to main and v-next branches, plus PR reviews. Initially it started modifiying my existing workflow that takess care of the Azure deployment. I wanted a separate workflow for testing, so I interrupted (that's nice I wasn't "forced" to wait), and asked it to create a new one instead. The result was the running-unit-tests.yml workflow that worked perfectly on the first try.

This was genuinely surprising. CI/CD configurations often require tweaking, but the generated workflow handled:

• Multi-version .NET setup
• Dependency restoration
• Building and testing
• Test result reporting
• Code coverage analysis
• Artifact uploading

The PR Enhancement Adventure

Here's where things got interesting. When I asked Copilot to enhance the workflow to show test results in PRs, it started adding components, then paused and asked if it could delete the current version and start from scratch.

I said yes, and I'm glad I did. The rebuilt version created beautiful PR comments showing:

• Test results summary
• Code coverage reports (which I didn't ask for but appreciated)
• Detailed breakdowns.

The Finishing Touches

No project is complete without proper status indicators. I added a test status badge to the README, giving anyone visiting the repository immediate visibility into the project's health.

Key Takeaways

What Worked Well

1. AI as a Learning Partner: Having Copilot explain testing concepts and xUnit features was like having a patient teacher
2. Iterative Refinement: The back-and-forth process felt natural and productive
3. Comprehensive Solutions: The AI didn't just write tests; it created a complete testing infrastructure
4. Quality Over Speed: While it took 4 hours, the result was thorough and well-structured

What I'd Do Differently

1. Be More Specific Initially: Starting with clearer scope would have streamlined the process
2. Set Testing Priorities: Identifying critical paths first would have been valuable
3. Plan for Visual Test Reports: Thinking about test result visualization from the start

Lessons About AI Collaboration

• Model Choice Matters: The difference between AI models was significant
• Conversation Quality Matters: Clear explanations make the collaboration more valuable
• Trust but Verify: Understanding every piece of generated code is crucial
• Embrace Iteration: The best results come from multiple refinement cycles

The Bigger Picture

This experiment reinforced my belief that AI coding assistants are most powerful when they're true collaborators rather than code generators. The value wasn't just in the 88 tests that were written, but in the learning that happened along the way.

For developers hesitant about AI assistance in testing: this isn't about replacing your testing skills, it's about augmenting them. The AI handles the boilerplate and suggests patterns, but you bring the domain knowledge and quality judgment.

Conclusion

Would I do this again? Absolutely. The combination of comprehensive test coverage, learning opportunities, and time efficiency made this a clear win. The 4 hours invested created not just tests, but a complete testing infrastructure that will pay dividends throughout the project's lifecycle.

If you're considering AI-assisted testing for your own projects, my advice is simple: start the conversation, be prepared to iterate, and don't be afraid to ask "why" at every step. The goal isn't just working code - it's understanding and owning that code.

The complete test suite and CI/CD pipeline are available in the NoteBookmark repository if you want to see the results of this AI collaboration in action.

Reading Notes #651

Welcome to another edition of my reading notes! This week brings some fascinating insights into AI's real-world impact, exciting developments in .NET and containerization, plus practical tools for improving our development workflows. 

From local AI-powered code reviews to Docker security hardening and the upcoming .NET 10 features, there's plenty to explore.

 

AI

• The promise that wasn’t kept (Salma Alam Maylor) - Interesting thoughts about AI and its impact on our work but also on our life, and the planet.

• Local code review with Docker and smollm2 before pushing to git (Gerardo Lopez) - This is a really cool idea! I'll have to try it.

Programming

• Converting a docker-compose file to .NET Aspire (Andrew Lock) - Cool experiment. I must say I did the same thing, and I encourage you to do it too!

• Inside GitHub: How we hardened our SAML implementation (Greg Ose, Taylor Reis) - Very interesting post that pushes the curtain a little bit so we could see behind the scene how this very used but notification system works and has been updated

• Announcing dotnet run app.cs - A simpler way to start with C# and .NET 10 - .NET Blog (Damian Edwards) - That's a really cool new feature (that we can test in C# preview), It will be so useful in automation!

Cloud

• Introducing Docker Hardened Images: Secure, Minimal, and Ready for Production (Michael Donovan, Nikhil Kaul) - Security is the concern of everyone. I like this idea of like more secure but still flexible container images. Have a look and see for yourself

• Podman vs. Docker: Containerization Tools Comparison (James Walker) - A nice post that explains the difference at a high level. This isn't a command-to-command comparison, but more scenarios and performance.

Miscellaneous

• Enhance productivity with AI + Remote Dev (Brigit Murtaugh, Christof Marti, Josh Spicer, Olivia Guzzardo McVicker) - I love the dev container environments, they are so useful! And I also use the remote one when I'm not on my dev device so easy. Happy to see that Copilot will be right there with me.

~frank

Reading Notes #650

It's time for another edition of Reading Notes! This week brings exciting developments in the open source world, with major announcements from Microsoft making WSL and VS Code's AI features open source. We've also got updates on Azure Container Apps, .NET Aspire, and some great insights on developer productivity tools.

 

Let's dive into these interesting reads that caught my attention this week.

Cloud

• Happy 5th Birthday Bicep! (Sam Cogan) - What?! Five years already! That's incredible, I remember all the discussion about how we make our business better and honestly, bicep is a big success. Congrats to the team

• Have I Been Pwned 2.0 is Now Live! (Troy Hunt) - New look, new merch, and confetti, all without API breaking changes! Learn all about this major update in this post.

• Announcing Workflow in Azure Container Apps with the Durable task scheduler – Now in Preview! (greenie) - Exciting news about a new service. It looks solid and perfect for integration scenarios. Looking forward to experimenting with it.

Programming

• Pushing a whole stack of branches with a single Git command (Andrew Lock) - I'm always amazed to learn how people use git. This post shares a very smart way to push clear feature in multiple branches

• What's new in .NET Aspire 9.3 (David Pine) - Wow! How so many great new features can be added in a single version?! Aspire is a must for all .NET developers.

• Accelerate Your .NET Upgrades with GitHub Copilot (McKenna Barlow) - That's the tool I've been waiting for ages! Adding a Copilot to the extension is the smartest move they could make. I'm going to update an app right away. I'll share more later

Open Source

• Edit is now open source (Christopher Nguyen) - That's a great news! I installed it half through the post and it great! Fast, simple, and tiny!! Love it!

• The Windows Subsystem for Linux is now open source (Pierre Boulay) - And another project that turns out to be open source, I love it, it's just fantasti,c read all the details and dispose

• VS Code: Open Source AI Editor (VS Code team) - I strongly believe in open source. Very happy to see this change!

AI

• Agent mode for every developer (Katie Savage) - Great new for everyone as the agent mode become available in so many different editor. This post also contains videos to shows some scenarios.

Podcasts

• Reimagining the Windows Terminal with Warp's Zach Lloyd (Scott Hanselman) - A very interesting talk with the CEO of Warp that answers so many questions I had about this very different terminal. Really interesting episode, and terminal too BTW)

• The power of empathy in leadership with Jerry Colonna (Macmillan Holdings, LLC) - This very interesting episode is about the power of empathy in leadership.

• 362. Maximal Fitness with Minimum Time with Ben Greenfield (Part 1) (Greg McKeown) - Interesting conversation with a triathlete about different ways to train and nutrition

Miscellaneous

• The experience is enough (Salma Alam-Naylor) - Whether we like it or not, we are people creature. We all need to stop hiding behind our screens and get out there!

~frank

Reading Notes #649

Welcome to another edition of my reading notes! This week I've come across some interesting articles spanning from programming decisions to career tips and AI innovations. Hope you find something valuable in this collection.

Programming

• Why we built our startup in C# (Sam Cox) - I really like those true-story blog posts; they teach us about the thought process and the reason behind a decision.

• It wasn’t the idea that failed: it was the execution (Salma Alam-Naylor) - Even though I feel like I'm missing a few points about sigma and new stuff coming up in 2025, this post is an amazing memory of our past in terms of evolution in the web industry

AI

• Accelerate AI innovation and business transformation (Byron Rader) - It's important to look forward, and you know what? There are people to help and guide you and your enterprise.

• Why APIs Are Essential and MCP Is Optional (for Now) (Gil Feig) - Great post that clarified the distinction between an API and the mCP servers. It's an interesting post.

Miscellaneous

• Thriving After a Layoff: The First 30 Days (scrappy girl project) - A friend of mine shared with me this post, and I think it will help me in the upcoming days. So here I am sharing so more can benefit from it

Books

• The Let Them Theory (Mel Robbins) - Stop wasting energy on things you can’t control. It something we all know, but probably forgot the power if it. Let go is hard, but it works in so many scenario. In this book Mel explains how to make it works, and how to use it with a let me action.
   

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 #648

Welcome to this week's reading notes! Dive into the latest on Microsoft's new AI chat template, explore Docker's MCP CLI, learn about integrating AI into .NET applications, and discover how to automate .NET MAUI library publishing with GitHub Actions. 

Whether you're interested in AI advancements, programming techniques, or DevOps practices, there's something valuable waiting for you below.

MsDevMtl Meetup - Uno

Suggestion of the week

• Exploring the new AI chat template (Andrew Lock) - This new .NET template looks pretty useful and has a lot of components already baked in. This post explains those and shows how to customize it for our usage.

Programming

• Crates and Dependencies: NuGet, Meet Cargo - Chris Woody Woodruff (Chris Woodruff) - Interesting comparison there, a bit more love toward Rust, I think, but that doesn't make this series less valuable.

• How to Host Blazor WASM on Docker (Rikam Palkar) - Nice post with all the code you need to reproduce.

DevOps

• Packaging and Publishing a .NET MAUI Library with GitHub Actions - .NET Blog (Sweeky , David) - I'm always amazed by what we can do with automation. Second post of a series on .NET MAUI.

AI

• Getting Hands-On with the Docker MCP CLI (Sarthak Varshney) - How to get, use, and connect the brand new MCP tool from Docker.

• AI Repo of the Week: GitHub Copilot Adventures (Dan Wahlin) - When open-source meets AI, and this time, games! Interesting series where AI-related repositories are featured.

• Microsoft.Extensions.AI: Integrating AI into your .NET applications (Japhlet Nwamu) - This package is amazing. It allows you to connect to many models hosted in many different places. This post is the perfect place to get started.

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 #647

This post is a collection of my latest reading notes, highlighting interesting articles and resources on AI, programming, databases, and more. Each link includes a brief summary of what I found valuable or noteworthy.

AI

• Getting Started with Azure MCP Server: A Guide for Developers (Lee Stott) - Quick post about this new feature.

• Protecting against indirect prompt injection attacks in MCP (Sarah , Den) - Security must be in our list of priorities in all types of projects. This post explains how we can secure them.

• How to build and deliver an MCP server for production (Colin McNeil) - That makes sense doctor is known to encapsulate and simplify the portability of application

Programming

• Set the default file encoding - Visual Studio Blog (Mark Downie) - Nice tip! As a developer who works daily on different operating systems, I know to well this issue.

• 4 real-life examples of using reflection in C# ( Ali Hamza Ansari) - Very interesting and useful post that go over 4 scenarios

• Microsoft Extends SLNX Solution File Support in .NET CLI - InfoQ - Have you tried yet the new format? It's still on my to-do list.

Databases

• DuckDB in Depth: How It Works and What Makes It Fast (Barry Smart) - This is a very interesting post that explains a little bit more how a vectoral database works and why it's so performant with documents

Miscellaneous

• Help yourself to thrive (Salma) - The human body is an extraordinary machine, extremely strong and conciliant, but it also requires a fine turning. Great post, we must learn from it.

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 #646

Welcome to this week's collection of fascinating reads across cloud computing, AI, and programming! As technology continues to evolve at breakneck speed, I've gathered some of the most insightful articles that caught my attention. From securing MCP servers to exploring Rust, there's something here for every tech enthusiast. 

Dive in and discover what's new in our rapidly changing digital landscape.

Cloud

• Azure API Management Your Auth Gateway For MCP Servers | Microsoft Community Hub (PranamiJ) - Why all the fuss about MCP, we must not forget security. This post suggests a simple solution.

AI

• How Azure Copilot Helped Me Quickly Troubleshoot a Demo (David Giard) - That's a good example of how AI can help you not do the job for yourself but avoid mistakes and do it faster.

• Secure Remote MCP Servers With Entra ID And Azure API Management (Den Delimarsky) - Nice solution in Python to secure your MCP servers

Programming

• When ASP.NET Core Identity Is No Longer Enough (Andrea Chiarelli) - Authentication and authorization have an important place in our Apps. This post shares details about how things work and the different processes.

• New Docker Extension for Visual Studio Code (Remy Suen) - This extension was already a must, they made it better, it's a must must! But seriously give it a try and try it by yourself.

• From C# to Rust: A 42-Day Developer Challenge (Chris Woodruff) - Cool tease of an experiment that promises a lot of learning.

• How to Programmatically Create MS Word DOCX Documents with .NET C# on Linux (Bjoern Meyer) - Cool package that helps create Word documents. Perfect when running in a Linux container.

• Preview 2 of the .NET AI Template Now Available (Jordan Matthiesen) - New templates with AI, Qadran and Aspire, oh boy life is good!

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 #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

• Calling MCP Servers in C# with Microsoft.Extensions.AI (Mark Heath) - Many options, new tools, fresh possibilities, it's only missing our ideas.

• If LLMs Can Code, Why Are We Building More IDEs? (Mark Downie) - That's an excellent question, and I agree with Mark.

• Understanding and mitigating security risks in MCP implementations (Sarah Young) - The MCP servers are opening many opportunities, and it's important to know the risk. This post is a must.

• Build MCP Remote Servers with Azure Functions (Matt Soucoup) - A quick post that shows how a serverless MCP server can be hosted Azure and be secure; all code included.

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

Selecting the Connection Type

GitHub Copilot supports several ways to connect to MCP servers:

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.

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.

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:

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

• Microsoft Copilot in Azure is now generally available | Microsoft Community Hub (Ruhiyyih Mahalati) - Oh wow! That was fast! If you haven't tried it yet, you should it's extremely useful and quick. Ask something about your resources or services you would like to use.

• Build a Model Context Protocol (MCP) server in C# - .NET Blog (James Montemagno) - A nice tutorial about the MCP server and how to use one in VSCode

Programming

• Generating architecture diagrams from .NET Aspire resources at publish time (Anthony Simmon) - This is one new feature that will be so useful. How many times did I need to refer to a diagram that was outdated.

• Exploring new .NET releases with Dev Containers - .NET Blog (Mike Kistler) - Really cool trick shared in this post. Yes, trying the new version in a container but how that container is build; that's cool!

• .NET Aspire 9.2 is Now Available with New Ways to Deploy - .NET Blog (Jeffrey Fritz) - This week was the release of Aspire new version, and it's packed with many features. The launch party video is also very interesting.

• Aspire: A Platform for Reusable Infrastructure (David Fowler) - For once, I think Aspire is the perfect name because it's inspiring.

• How we ended up rewriting NuGet Restore in .NET 9 - .NET Blog (The NuGet Team) - A very interesting article that explains how a tool that all .NET developers use got rewritten

• Porting Code with LLMs (Mark Heath) - It's always interesting to see how people use AI to help them do their work. Love it!

Podcasts

• Per Kops: Architecture of Ollama and Local LLMs - Episode 342 (Azure & DevOps Podcast) - An interesting discussion about Olama (local LLMs), .NET architecture, and Semantic Kernel.

• Vertical Slice Architecture with Jeremy Miller (.NET Rocks!) - This episode is about Vertical Slice Architecture, what it is, when it makes sense to use it, and some comparisons with the others that we know.

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

• Azure SDK Release (March 2025) (Hector Norzagaray) - Many languages are supported and now Rust is part of it. There also some new bits for Node and Python.

• Azure Developer CLI (azd) - April 2025 (Kristen Womack) - New features in the CLI, bug fixing and new possibilities in the website to search templates!

Databases

• Are You Azure SQL Database Curious? (Karen Lopez) - What?! Didn't know about that free tier. I could definitely use that; great news!

AI

• Does AI really make you more productive? (Salma Alam-Naylor) - I trust AI as much as I trust any code found after googling.Meaning it might works but to I need to understand what it is doing. There is no trust, is always gambling.

• Microsoft partners with Anthropic to create official C# SDK for Model Context Protocol (Mike , Maria) - New SDK is already available and it works!

Programming

• .NET Aspire - Microsoft's Attempt at Infrastructure as Code (darren horrocks) - This is a quick intro to .NET Aspire, perfect to learn what it is without going deep into the details.

• Making Software Like LEGO: How Aspire Brings the Pieces Together (David Fowler) - I really liked that image with the construction blocs. And also it seems my hobbies didn't change much in the past fifty years.

Podcasts

• Forking around (with the Linux Desktop) and Finding Out with Justin Garrison (Hanselminutes with Scott Hanselman) - Interesting discussion about Linux desktop and everything they can do. More people should know about that

• 359. Rest More, Stress Less, and Live the Life You Actually Want with Courtney Carver (The Greg McKeown Podcast) - Episode with the author of the book Gentle: Rest More, Stress Less, and Live the Life You Actually Want. It seams simple but must be hard to apply in today's word.

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

• Hello HybridCache! Streamlining Cache Management for ASP.NET Core Applications - .NET Blog - Already GA! Wow, great library that really simplifies having the best cache experience possible.

Programming

• Blazor Basics: Handling Errors and Exception Logging (Claudio Bernasconi ) - This nice post explains the fundamentals about the errors with Blazor.

AI

• Selecting the right model for coding (Mark Downie) - Nice post that answers a question, that I'm sure many of us thought without really knowing the answer.

Miscellaneous

• Announcing Dapr AI Agents (Mark Fussell, Yaron Schneider, Roberto Rodriguez) - I like those tech savvy agent that knows about one thing. I f|l I can trust them more and it usually go faster.

• Mastering GitHub Copilot: When to use AI agent mode (Andrea Griffiths) - Using copilot the "good way" can and will definitely improve your productivity. This post helps you to get started

• Xbox + .NET Aspire: Transforming Local Development Practices (Craig Taylor) - Since I started using Aspire, I want to use it everywhere. Yes, it's that good and this story is just another proof.

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!

prompt: Web dev in a D&D monsters card style

 

Suggestion of the week

• Profiles in Visual Studio Code - I used two profiles to control an extension. But after reading this, I may create more! I have so many ideas.

Cloud

• Hello HybridCache! Streamlining Cache Management for ASP.NET Core Applications - Already GA! Wow, a great library that simplifies have the best cache experience possible.

Programming

• Introducing support for SLNX, a new, simpler solution file format in the .NET CLI - The XML format for the solution file has been around but no it's supported everywhere. "dotnet sln migrate" to convert yours.

• .NET Aspire Integration Testing Quick Start (James Gould) - This is a nice post sharing tips and tricks about .NET and unit test.

AI

• Introducing Azure AI Foundry — Everything you need for AI development (Zachary-Cavanell) - Quick intro whatinis and how to get started. There is the video and transcript.

Miscellaneous

• The Principal Developer Advocate Paradox: Scaling Impact Without Burnout (Dewan Ahmed) - Yes, that's exactly that. I think all jobs have theirs completely, but the advocate is definitely one that is hard to understand and measure.

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

• Azure Developer CLI (azd) - March 2025 - The azd CLI just got better, with some new features, improved error messages, and of course bug fixes. Don't forget to update your version.

• Dapr in Two Minutes: Simplifying Distributed Application Development (Whitney Lee) - A great explanation of Dapr. Spoiler, it's a great tool.

AI

• .NET AI Template Now Available in Preview (Jordan Matthiesen) - .NET new AI stuff, I love it! You can add new templates for you 'dotnet new' to get AI project!

Programming

• .NET Aspire and Dev Container (Laurent Kempé) - DevContainers are really a game changer. You don't have to be a container guru to use it, and it will make a dev environment constant everywhere on any device.

• A 10x Faster TypeScript - TypeScript (Anders Hejlsberg) - Very impressive results. The video is great.

• .NET Aspirations - Embracing OpenTelemetry (Alexandre Nédélec) - This nice post explains how the open telemetry is set in .Net Aspire Dashboard.

~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

• Some observations while writing my first Azure Function (Tim Deschryver) - I really like those types of posts where we follow the journey of the author going through learning or completing tasks.

Programming

• Great new productivity features in Visual Studio - Visual Studio Blog (Mads Kristensen) - Wow, there are so many cool features! I personally love the new line wrap and horizontal scroll bar—little details that make a big difference.

• Is this the next step in the evolution of front end dev? (Salma Alam-Naylor) - I never used those frameworks, but I'm curious now and will have to try.

• What are Custom Integrations in .NET Aspire? (Kalle Marjokorpi) - This second post in a series shows how to configure the identity server name Curity. It's implemented in a .NET Aspire solution and looks very well structured.

AI

• Unlock new possibilities for AI Evaluations for .NET - .NET Blog (Wendy Breiding (SHE/HER)) - That looks like a cool plugin for Azure DevOps Pipeline

• Announcing new models, customization tools, and enterprise agent upgrades in Azure AI Foundry | Microsoft Azure Blog (Asha Sharma) - So many models and plenty of new features, that's a great update!

Miscellaneous

• 5 Learning techniques you should know (Marco Siccardi) - Learning how to learn is a concept that in underrated. This post shares 5 accessible tips with big impact.

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

• Azure Functions – Part 1 (Jesse Liberty) - Quick launch of a series about Azure Function.

• How to Multistream Using Azure, Azure VM, MonaServer 2, and FFmpeg with OBS Studio (Maho Pacheco) - That's a very cool idea! This post also made me understand better how those things work.

Programming

• Dapr v1.15 is now available (Dapr project maintainers ) - This new release is anticipated by the community with new features and many bug fixes

• Building a CRUD API with ASP.NET Core Web API and PostgreSQL (M. Oly Mahmud) - This is a nice step-by-step tutorial with all the code snippets required to get started.

• .NET Aspire 9.1 is here with six great new dashboard features, and more! - .NET Blog (Maddy Montaquila) - Learn more about many dashboard updates in this post like the grouping, theme, localization and logs management.

AI

• Let's Learn .NET: GitHub Copilot Event - .NET Blog (James Montemagno) - A new cool event is coming up to improve our productivity. Learn how to use copilot as a developer.

• Claude 3.7 Available for Visual Studio - Having options is interesting, I should try Claude to see the difference.

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

• Azure Developer CLI (azd) - February 2025 (Kristen Womack) - Nice to see the work of this very active team.

Programming

• 5 tips for promoting your open source project (Klint Finley) - Great tips to promote your OSS project.

• C# Dev Kit Updates: .NET Aspire, Hot Reload, and More! - .NET Blog (Wendy Breiding (SHE/HER)Wendy Breiding) - Great updates that really make a difference. I'm already a fan of that improved Add Aspire experience.

• Announcing Our Work on a Blazor Component for Document Editing and Viewing (Bjoern Meyer) - Looking for fancier components have a look at this new one that you can try for free.

AI

• Announcing Generative AI for Beginners – .NET - .NET Blog (Pablo Lopes) - A new set of lessons to learn AI in c#. It's free and it's all available directly from a GitHub repo. You should go fork it right now!

Miscellaneous

• 3 reasons you should tour a conference talk (Salma) - I totally agree on the value of doing a session multiple times. However, sometimes finding opportunities can be hard.

• How I created a newsletter I actually enjoy writing (Salma) - Enjoy the moment! If you like what you do, it should help doing it right and keep doing it.

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