In this session, we'll dive into the Model Context Protocol (MCP), an open standard that's revolutionizing how developers connect AI models to data sources and tools. MCP has been proclaimed to be a "USB-C for AI applications" and in this session we will explore whether it delivers on its promise to provide a universal interface that standardizes interacting with LLMs. We'll see how MCP eliminates the complexity of building custom integrations for each AI provider, allowing you to focus on creating value rather than maintaining connectors. You will learn how to create an MCP server that enables your applications to securely access domain-specific knowledge, execute tools, and maintain context across interactions, all while preserving the flexibility to switch between LLM providers without rewriting your integration code.

The practical benefits of MCP extend beyond architectural simplicity. We will look at how MCP helps you build more capable AI agents by providing them with the exact context they need at runtime - whether that's accessing a RAG knowledge base, executing specialized tools, or fetching live content from the internet. We'll also look at how to create a custom MCP client application that uses a custom server and harnesses the power that it exposes. Could MCP be the foundation for your next generation of AI-powered applications that are more capable, secure, and adaptable? Join this session to find out!