Let's learn about the Model Context Protocol (MCP)! A cutting-edge framework designed to standardize interactions between AI models and client applications. Through this beginner-friendly session, we'll introduce you to MCP and guide you through creating your first MCP server.

Just as HTTP connected the web, MCP connects AI. This session explains how the Model Context Protocol helps AI models access real data, perform actions, and stay grounded in context — with a live demo to see it in action.

Hands-on lab session continuing Part 1, containerizing and deploying the AI agent and validating GPU-accelerated deployment on Cloud Run.

Hands-On Lab (Part 1): Secure and deploy a Model Context Protocol (MCP) server and start integrating the Agent Development Kit (ADK) to empower an intelligent agent.

Hands-on lab session focusing on building and securing production-ready services on Cloud Run, including setting up an MCP server and authentication.

This session dives into an AI-accelerated development technique for building and deploying a Gmail Add-on. We'll explore integrating Gemini CLI for AI-assisted development, Google Apps Script for backend logic and Workspace integration, and the Model Context Protocol (MCP) to connect Gemini CLI to Google Workspace tools and Google Workspace developer documentation. Join us to gain the practical knowledge needed to extend Gmail's capabilities with modern generative AI features.

Discover how to seamlessly integrate AI applications and agents into Azure AI Foundry using the Model Context Protocol (MCP). In this session, we will explore how MCP enables direct connections to existing knowledge servers and APIs, allowing actions and knowledge to be automatically added and updated within your agents. Learn how this integration simplifies the agent-building process, reduces maintenance efforts, and leverages enterprise security and governance controls such as Virtual Network integration, Data Loss Prevention policies, and multiple authentication methods.

AI is evolving into autonomous agents that connect with multiple business systems via the Model Context Protocol (MCP). While these agents boost efficiency, they also introduce new security risks. They can access sensitive data and act across systems, sometimes without human oversight. This session covers key risks, real-world examples of failures, and practical ways to keep AI agents secure and trustworthy.

AI is evolving into autonomous agents that connect with multiple business systems via the Model Context Protocol (MCP). While these agents boost efficiency, they also introduce new security risks. They can access sensitive data and act across systems, sometimes without human oversight. This session covers key risks, real-world examples of failures, and practical ways to keep AI agents secure and trustworthy.

In an era where everything even slightly related to generative AI is considered the new meta, it is hard to keep track of the technical increments that are actually useful to our work and domains. The announcement of the Model Context Protocol from Anthropic has generated a lot of buzz and is a good attempt to become the leader among the various LLM providers. This talk will take a stab at creating an overview and an honest take on what the MCP server will bring us and what it feels like to develop one for Mollie, trying to combine all emotions and experiences together to answer the question of whether it really lives up to the promise. Defying established presentation best practices, I will try to live-code a new MCP server providing functionality for a to-be-chosen service.

Lets take a sneak peak into the open-source MCP community registry. A publish once, consume anywhere project for Model Context Protocol servers being developed by the MCP steering committee. In this 30 minute session we'll talk to the project leaders and unpack how server authors can publish their servers and how different registries and marketplaces can stay up to date with the latest MCP servers.

Think you’ve seen what Model Context Protocol can do inside Visual Studio Code? Think again. In this rapid-fire tour, we’ll flip every switch and surface every hidden gem. Expect zero slides and maximum keyboard: a full-throttle demo that leaves you with the shortcuts, settings, and insider tips to make VS Code the ultimate MCP-powered workbench.

Join Jay Parikh, Microsoft EVP of Core AI, as he opens MCP DevDays with an exciting look at how the Model Context Protocol is revolutionizing AI application development. Discover why Microsoft is all-in on MCP and how it's accelerating developer productivity across VS Code, GitHub Copilot, Azure AI Foundry, and Windows. This keynote features lightning demos showcasing real-world MCP implementations. Whether you're a developer, tool builder, or AI enthusiast, this session sets the stage for two days of hands-on learning about the protocol that's defining the next generation of intelligent

This session introduces the AI Gateway pattern—a critical architectural component that serves as the central control plane for enterprise AI ecosystems. We'll explore how AI gateways solve real-world challenges through unified API abstraction, intelligent failover mechanisms, semantic caching, centralized guardrails, and granular cost controls. You'll learn practical architectural patterns for building high-availability gateways that handle thousands of concurrent requests while maintaining sub-millisecond decision-making through in-memory operations. We'll dive deep into the technical architecture, covering separation of control and data planes, asynchronous logging patterns, and horizontal scaling strategies. The session will also look ahead to emerging patterns like Model Context Protocol (MCP) integration, where gateways will manage not just model access but entire tool ecosystems, enabling natural language automation across enterprise software. Whether you're an architect planning your AI infrastructure, a platform engineer managing multi-model deployments, or a technical leader navigating AI governance challenges, this session provides actionable insights for building resilient, scalable AI systems. You'll leave with concrete patterns, architectural blueprints, and a roadmap for implementing centralized AI control planes that grow with your organization's AI maturity. Key takeaways include gateway design principles, performance optimization strategies, multi-provider management patterns, and a practical framework for evaluating AI infrastructure needs in your organization.

Damien will talk about how Not In My Back Yard (NIMBYISM) is strangling UK infrastructure development, particularly renewable energy projects, and demonstrate his novel solution: the Nimby Radar - an AI-powered system that quantifies the true cost of local opposition to green infrastructure. He'll dive into publicly available data sources to map organized resistance efforts, then showcase how Google's latest AI capabilities - including Model Context Protocol (MCP), agent-to-agent communication, advanced vectorization, and large-scale data analysis APIs - can automatically identify and analyze NIMBY campaigns at scale.