From Clicks to Commands: AI for Editors, Developers, and Everyone Else
What happens when you give AI access to Umbraco’s full set of tools? With the Model Context Protocol (MCP) for Umbraco, we’re seeing AI chain tasks together in powerful and often unexpected ways—like handing it a box of LEGO bricks and watching it build something surprisingly intelligent.
In this session, we’ll show you how MCP enables AI agents to interact directly with Umbraco’s Management API, uncovering new, creative ways to automate tasks that would usually require tedious manual work in the UI. From content creation to bulk updates and beyond, the possibilities are endless—and the results are eye-opening.
We’ll also give you a peek behind the curtain, showing you how the system is built and how easy it is to integrate Umbraco MCP with Claude, no deep AI expertise required.
How We Integrated an AI Agent to Talk to Umbraco
Join us on a journey through the creation of a Model Context Protocol (MCP) server for Umbraco using TypeScript. What began with manual coding and schema discovery evolved into a streamlined, AI-accelerated workflow using Orval, Zod, and Cursor’s IDE with custom AI agent rules.
We’ll walk through how we moved from a basic prototype to a fully featured MCP server—one that mirrors the capabilities of the Umbraco backoffice without compromising security. Along the way, we’ll share how integrating AI into our development process reshaped our approach, and we’ll even demonstrate what an agent can do once it’s empowered with structured access to Umbraco.
What you should be testing in Umbraco?
Join me in exploring the world of unit testing in Umbraco. Discover how to effectively implement server-side testing to ensure the stability and reliability of your website. You'll learn about the key areas where testing can make a significant impact and how to identify those areas. Did you know that Umbraco provides a convenient Nuget package for integration testing? This session will teach you how to use this package and other essential tips, tricks and tools to improve your unit testing process.
Fun with flags
Looking at Microsoft.FeatureManagment and the many ways it can be used all without reducing your editors experience.
Feature management provides you with the power to enable/disable almost anything within your project, with the addition of feature filters you can even A/B test and create personalized experiences based on practically anything.
We will we go through how this is setup and run through some of the use cases, along with a little package magic to make sure your editor is never bothered by properties that do nothing.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top