Beyond the Book: Kyle Stratis on AI Agents with MCP
Published by O'Reilly Media, Inc.
Model Context Protocol for building clients, servers and end-to-end agents
As AI agents become more capable, connecting them to the tools, data, and services they need has become one of the biggest challenges in building production-ready systems. Anthropic’s Model Context Protocol (MCP) has quickly emerged as a leading open standard for solving this problem, giving developers a consistent way to integrate agents with external resources and build more capable, interoperable AI applications.
Join Kyle Stratis, author of AI Agents with MCP, for a practical discussion of how MCP is transforming agent development. Drawing on hands-on experience, Kyle will explain the protocol’s core concepts, demonstrate how to build MCP servers and clients in Python, and share best practices for designing scalable, model-agnostic agent architectures that can evolve alongside the rapidly changing AI ecosystem.
Whether you’re a software engineer, AI developer, architect, or technical leader building agentic applications, you’ll leave with a solid understanding of MCP and practical guidance for designing, implementing, and extending AI systems.
Join us each month for Beyond the Book, a live series hosted by Vicki Reyzelman, featuring in-depth conversations with the authors shaping technology today. From AI and data science to software architecture, cybersecurity, leadership, and beyond, each episode explores the ideas behind the latest books and the real-world challenges that inspired them. Stay ahead of industry shifts and get a glimpse into the thinking driving today’s most influential technology books with a front-row seat to these thoughtful discussions.
What you’ll learn and how you can apply it
- Explain MCP’s core architecture and how it standardizes the connection between AI agents, tools, data, and services
- Build MCP servers and clients in Python to give agents reliable access to external capabilities
- Apply practical design patterns for creating scalable, model-agnostic agent architectures that can adapt as tools, models, and requirements evolve
This live event is for you because...
- You’re building AI agents that need to connect safely and reliably to real-world tools, data sources, and services.
Prerequisites
- Come with your questions for Kyle Stratis
- Have a pen and paper handy to capture notes, insights, and inspiration
Recommended follow-up:
- Read AI Agents with MCP (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Friday, December 4, 2026, at 7:00am PT / 10:00am ET
- Interactive discussion and Q&A (30 minutes)
Your Hosts and Guests
Vicki Reyzelman
Vicki Reyzelman is a senior solutions engineer at Akamai, where she helps organizations around the globe protect and secure their online applications. She’s worked extensively in the fields of cloud integration, security, API ecosystems, and software development and has written dozens of blog posts and articles on technology solutions to business problems and on technology trends for e_Week_ magazine. She’s also a patent holder for a search assistant technology at Yahoo! Vicki holds an AI certificate from MIT, an MBA from Georgia State University and a bachelor’s degree in computer science from Kennesaw State University.
Kyle Stratis
Kyle Stratis is the founder and principal consultant of Stratis Data Labs, where he provides startups and large firms alike with his expertise in AI engineering, computer vision, data engineering, and machine learning platform engineering garnered over a decade as a software engineer. In addition to designing data architecture, building AI platforms and agents, and migrating analytics workflows to the cloud for his clients, he writes about Python, LLMs, and personal knowledge management on his blog Edge Cases.