Model Context Protocol Fundamentals
NewTired of staring at the chat box of an AI assistant wishing it could actually do a task for you rather than just telling you what to do? Model Context Protocol (MCP) is the glue between an AI agent and your data and tools. With MCP, AI assistants can read your documents, conversations, and other context and take action for you by sending emails, submitting tickets and more. But what really is MCP and how do you use MCP servers safely in practice as part of your day-to-day workflow? This half-day course introduces MCP and dives into practical use cases. Laurel will walk you through how to build and deploy simple MCP servers, configure different clients to use MCP servers and build workflows using skills or prompts. This will be a hands-on session aiming to help you use MCP in production.
Prerequisites:
Attendees that get value from the workshop are most likely a software developer who:
- Is already using GitHub Copilot, Cursor, Claude Code or a similar AI coding assistant
- (Recommended) Is familiar with Google Drive and GitHub
- (Recommended) Light familiarity with python as that’s the language we will be building the MCP servers in
Laurel Orr is a Staff AI Engineer at Stacklok building AI systems to help enterprises unlock AI automation through better business context management, shared workflows, and scalable tool use. Prior to joining Stacklok, she was a PostDoc at Stanford researching generative AI and how it can tackle data management challenges. She was also a founding engineer at NumbersStation, an AI startup automating business analytics through structured data agents. Laurel has been building generative AI systems and prompt whispering since before ChatGPT and believes the key to better AI is better context.