The Model Context Protocol (MCP) is rapidly becoming the backbone for AI -based systems that need access to external data, but with great power comes great responsibility, especially when securing server implementations. In this conversation with Nate and Wils, founding engineers at Arcade.dev, we’ll explore advanced security patterns for MCP servers, from OAuth 2.1 flows and token validation to defending against confused deputy attacks, session hijacking, and token passthrough vulnerabilities. We’ll also highlight how all of this accrues to the emerging agentic space, where the interactions are no longer constrained to humans in the loop.

How do you let any MCP-aware agent tap into your platform? Build a remote server! In 30 minutes, Toby P. provides first-hand insights behind building GitHub’s remote MCP server. Then Joe Z. will follow up by building up a fresh remote server live, using the open-source MCP SDK. Walk away with a clear blueprint to launch your own remote MCP server before the day is done.

How do you let any MCP-aware agent tap into your platform? Build a remote server! In 30 minutes, Toby P. provides first-hand insights behind building GitHub’s remote MCP server. Then Joe Z. will follow up by building up a fresh remote server live, using the open-source MCP SDK. Walk away with a clear blueprint to launch your own remote MCP server before the day is done.

An in-depth look at the MCP C# SDK including demos of all the new features in the 2025-06-18 spec.

An in-depth look at the MCP C# SDK including demos of all the new features in the 2025-06-18 spec.

The best way to learn is to do! In this session we are going to use Agent mode to teach us the basics of MCP and implement a server in less than 30 minutes. Can we do it Lets see...

The best way to learn is to do! In this session we are going to use Agent mode to teach us the basics of MCP and implement a server in less than 30 minutes. Can we do it Lets see...

Day 2 shifts into high gear for builders. This keynote sets the stage for a deep dive into MCP implementation, showcasing how to move from proof-of-concept to production-ready MCP servers. Learn the essential building blocks—Azure Functions, API Management, and security best practices—that power scalable MCP solutions. We'll demonstrate prompt-driven development workflows, explore real-world architectures, and reveal how leading organizations are already shipping MCP-powered features. Whether you're building for the enterprise or the edge, this session provides the blueprint for creating secure, scalable MCP servers that transform AI agents from demos into deployed solutions. Get ready to build.

Visual Studio now speaks MCP. In this fast-paced session you’ll learn how the IDE’s new Model Context Protocol tooling turns agent-ready APIs into a first-class experience

The Model Context Protocol now fully embraces OAuth 2.1 conventions, bringing mature authorization patterns to AI agent ecosystems. Rather than inventing new auth mechanisms, MCP adopted proven OAuth flows, dynamic client registration, as well as the brand-new Protected Resource Metadata conventions. This session explores how the new spec significantly simplifies the developer experience for both MCP client and server implementers, as well as gives developers more flexibility around integration with existing authorization servers.

What if every website could talk back—understanding a visitor’s plain-English question and answering with the exact insight (or next action) they need? In this fireside conversation, Ramanathan Guha— web-standards pioneer (RSS, Schema.org) and the creator of NLWeb—joins core engineers from the project to explain how Microsoft’s new open initiative is turning that vision into reality and how MCP falls into the big picture.

Foundations with ADK: an introduction to building AI agents using ADK, covering fundamental concepts, architecture, and best practices.

Foundations with ADK — first session in a five‑session series on AI agents focusing on ADK, MCP and A2A; includes theory and live coding.

FastMCP & Tool Integration: exploring FastMCP and tool integration patterns for AI agents.

FastMCP & Tool Integration — second session focusing on MCP and tool integration within AI agents; theory and live coding.

Episode 2: FastMCP & Tool Integration.

Live demonstration of connecting agents built by Google DeepMind, DataStax, and Arize AI in real time.

See how real-time pipelines and the Model Context Protocol help agents make better decisions. Expect a full-stack walkthrough—no fluff.

A propos du talk : Les agents IA sont des programmes qui agissent de manière autonome : pour cela, ils doivent être capables de communiquer de manière programmatique avec une IA, et d'effectuer des actions.Dans cette session, allons voir:Les Structured Outputs : comment obliger une IA à répondre en suivant un schéma JSON, de manière à pouvoir mapper ce résultat avec des objet JavaLe Function Calling : comment définir et appeler des functions Java depuis un modèle IAMCP: le nouveau protocole qui standardise comment les LLM communiquent avec différentes sources de données et outilsNous utiliserons le code, les démos et la documentation que j'ai réalisés pour implémenter ces fonctionnalités dans LangChain4j en utilisant le tout nouveau SDK Java développé par OpenAI.