The Power Apps MCP (Model Context Protocol) Server is now in public preview. It exposes three tools — invoke_data_entry, request_assistance, and log_for_review — that let AI agents automate tasks inside model-driven apps with built-in human supervision via a redesigned agent feed. This guide covers every feature, technical detail, current limitation, and step-by-step setup path.
This guide shows Power Platform developers how to use Terraform to provision and manage Azure resources — Key Vault, Storage, Function Apps, API Management, and App Registrations — and integrate the full infrastructure lifecycle into GitHub Actions and Azure DevOps pipelines. All code samples are production-ready and environment-parameterized.
After half a year building production applications with Power Apps Code Apps, I'm convinced we're witnessing a fundamental shift in enterprise development.
Where Microsoft Technology Meets Intelligent Coding
I’m Zsolt Zombik, a senior Power Platform developer at ELCA Informatik AG, working at the intersection of Microsoft Power Platform and AI-assisted software development.
This blog is not about shortcuts, hype, or “10x developer” promises.
It is about building real, enterprise-grade Power Platform solutions—applications that implement complex business logic, enforce strict security models, scale to large datasets, and run reliably in production.
Everything shared here is based on hands-on, production experience, not theory.