Model Context Protocol (MCP) in Azure: Simplifying Agentic AI Integrations

Agentic AI has immense promise with its ability to complete complex tasks in complex environments. But building such agents requires orchestration and integration into a diverse range of tools and data sources. Until now that has required building bespoke integration and logic to wire together these different tools and sources. MCP to the rescue. The Model Context Protocol (MCP) is an open standard designed to enable seamless communication between AI models and external data sources, tools, and services. Think of it as a "USB-C port for AI applications", providing a universal way for AI systems to connect and interact with diverse tools and data repositories. In this session we discuss and demo: - The architecture and functionality of MCP - Support for MCP in Azure - The good, the bad and the ugly of MCP About the Speaker: Todd Whitehead is an experienced Azure consultant and Solution Architect with a focus on AI applications, Cloud Native Architecture, App Modernisation, Integration and developer productivity. He has over 30 years of experience across a range of industries including Financial Services, Energy, Mining, Retail and Public Sector helping customers deliver on their transformation ambitions. As a lifelong learner Todd loves every opportunity to both share that knowledge and learn from others and has presented at Australian and international conferences and user groups as well as at internal Microsoft and strategic customer events.