AI agents are evolving from text-based assistants into systems capable of performing real-world tasks. The Model Context Protocol (MCP) is an open standard that allows AI models to interact with external tools, data sources, and services through a common interface.

In this session, we will explore how MCP enables AI agents to execute actions beyond their initial context. We will demonstrate how to implement MCP in agents built with Semantic Kernel using C#, and how these agents can use tool calling to complete tasks. We will also touch on how MCP fits into the Azure AI Agent Service and how it supports scalable, secure agent design in enterprise scenarios.

Attendees will learn how to:
- Connect AI agents to external tools and data sources using MCP
- Implement MCP in Semantic Kernel agents with C#
- Use Azure AI Agent Service to run agents securely at scale

This session is intended for developers and architects interested in building AI agents capable of performing actions in the real world.