It was a pleasure to present at the .NET Developer Community in Peterborough on Thursday, January 29th. My talk, “Building Agentic .NET 10 Applications with the Model Context Protocol (MCP),” delved into how the Model Context Protocol (MCP) and advancements in .NET 10 are combining to form a unified platform for AI development.
The key objectives for the session were to:
One of the biggest challenges in building AI applications is providing the model with the right context. Without it, AI models can struggle to understand the user’s intent, leading to irrelevant or inaccurate responses. We’re moving from a world of fragmented tool integration chaos to one of simplified, streamlined agency, and MCP is the key.
The Model-Context-Protocol (MCP) is a new open protocol, backed by industry giants like Microsoft and Anthropic, that standardizes how applications provide discovery, actions, and context to LLMs.
Think of it like USB-C but for AI. It’s a universal standard designed to simplify the complex web of connections between AI models (Hosts) and external tools and data sources (Servers).
The talk also focused on the exciting developments in the .NET agentic ecosystem. An agent is a semi-autonomous piece of software that can be given a goal and will work to achieve it without needing step-by-step instructions.
With .NET 10, we are seeing the evolution of standalone libraries like Semantic Kernel and AutoGen into a Unified .NET 10 Agent Framework. This cohesive, vendor-agnostic orchestration layer simplifies interaction with various LLMs through clean abstractions like the IChatClient interface, all part of the new System.AI namespace.
The session included a live coding demo of how to implement MCP in a .NET 10 application using Visual Studio “26”. We built a simple chatbot that used MCP to provide context-aware responses to user queries.
The demo showed how to:
There were a lot of great questions from the audience. Some of the key topics we discussed were:
This topic is especially relevant for:
On a personal note, traveling to Peterborough was a wonderful experience. It’s a beautiful city, and the train journey from Sheffield via Doncaster was smooth and easy.
A big thank you to the .NET Developer Community in Peterborough for hosting the event!
Event Link: Building Agentic .NET 10 Applications with the Model Context …
Presentation Slides: The Model-Context-Protocol (MCP) in .NET
Speaker: Olorunfemi Davis, Senior Platform Engineer at Inflo
Hashtags: #MCP #DotNet #AI #Peterborough #Community #Speaking #CSharp #AgenticAI #DotNet10
A recap of the presentation on Building Smarter Apps with Microsoft Copilot Studio and .NET at the Birmingham .NET & Xamarin User Group.
A recap of my session at DevFest Bletchley Park in Milton Keynes, exploring a groundbreaking approach to bringing Gemini Nano directly to the browser, enabling a new class of offline-first, off-device web applications and Chrome Extensions.
A recap of my session at GDG Ado-Ekiti's 'Road to DevFest 2025', where I presented on using Gemini Nano for high-performance, offline-first browser extensions.
Recap of our in-person .NET Sheffield event: Building a cultural StoryBot with MCP, C#, and AI—blending cultures.
Recap of a GDG Cloud North West session in Manchester, exploring offline Gemini Nano apps in the browser, AI APIs, and practical developer insights.
Exploring the intersection of technical innovation and cultural storytelling. Recap of a .NET York session on building a cultural StoryBot with MCP, C#, and AI.
A recap of my talk at the .NET Meetup North East, where we explored the developer's role in an AI-first world, diving into Copilot Studio, .NET 9, and Semantic Kernel.
A recap of my lightning talk at .NET Liverpool, where I explored the new AI-first strategy in .NET 9, the Microsoft.Extensions.AI library, and how Semantic Kernel orchestrates AI intelligence in .NET applications.