MCP is more than tools. Through non-tool capabilities and brand-new discovery mechanisms introduced in the latest protocol spec, we can use MCP as a vehicle for agentic orchestration and definition. Through the power of declarative agents we move from code to configuration, with all the many advantages provided by that paradigm.

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, Sandra will introduce you to MCP and guide you through creating your first MCP server with Langchain4j and Quarkus.

Dans cette présentation, nous explorerons le protocole MCP (Model Context Protocol) et sa mission pour standardiser la communication entre nos applications et les LLMs. Nous commencerons par examiner les composants essentiels à la communication entre un client et un serveur, les différents protocoles de transport et les éléments constitutifs, notamment les outils, les prompts et les ressources. Nous aborderons ensuite des cas d'utilisation concrets, illustrant l'impact déjà significatif de MCP pour coder et intégrer de l'IA. Enfin, nous verrons comment l'écosystème Go adopte ce protocole pour permettre un développement MCP robuste et une nouvelle génération d'expériences de programmation.

Hear from Google Cloud experts and put your learnings into practice as you learn first-hand how to architect and deploy sophisticated agents and multi-agent applications and get hands-on with the latest cutting edge Gemini 2.5 models, the Google Agent Development Kit (ADK) framework, and key concepts like A2A and MCP.

Les serveurs MCP sont des composants essentiels pour améliorer la pertinence du code généré par les LLMs. Après une brève présentation des concepts, nous allons voir ce qu’il est possible de réaliser à l’aide des serveurs MCP Terraform et Vault.

MCP & Tool Integration

MCP & Tool Integration

Episode 2 – MCP & Tool Integration.

MCP and tool integration for AI agents; theory and live coding.

Oracle brings the power of AI to the database with Oracle Database 23ai. By now, you've probably heard about Oracle Database 23ai AI Vector Search, which essentially transforms the Oracle Database into a powerful, best-in-class Vector Database. But there are many more new innovations introduced to support all manner of AI workloads, and best of all, Oracle makes it easy to start using these tools without having to learn any new programming languages or frameworks. All of these AI innovations can be used today without any additional installation necessary, and can be accessed using your favorite code editor or IDE. Perhaps there's a problem you are trying to solve with AI today and don't know where to start? This is the session to get you there. In this session, you will learn how to: - Load embedding models into the Oracle database. - Run AI Vector Search in your database using regular SQL - Build Agentic RAG operations with Oracle 23ai. - Accelerate your AI similarity search operations with HNSW and IVF_Flat indexes. - Communicate with your database using natural language prompts with MCP. - Use AI to generate synthetic table data. - Use AI for document summarization inside the Oracle database.

Oracle brings the power of AI to the database with Oracle Database 23ai. By now, you've probably heard about Oracle Database 23ai AI Vector Search, which essentially transforms the Oracle Database into a powerful, best-in-class Vector Database. But there are many more new innovations introduced to support all manner of AI workloads, and best of all, Oracle makes it easy to start using these tools without having to learn any new programming languages or frameworks. All of these AI innovations can be used today without any additional installation necessary, and can be accessed using your favorite code editor or IDE. Perhaps there's a problem you are trying to solve with AI today and don't know where to start? This is the session to get you there. In this session, you will learn how to: - Load embedding models into the Oracle database - Run AI Vector Search in your database using regular SQL - Build Agentic RAG operations with Oracle 23ai - Accelerate your AI similarity search operations with HNSW and IVF_Flat indexes - Communicate with your database using natural language prompts with MCP - Use AI to generate synthetic table data - Use AI for document summarization inside the Oracle database.

Session on MCP and tool integration for AI agents.

Learn how to build an Azure AI Foundry Agent that leverages MCP. In this session we will be using the Foundry Agents Service to build a sales data analytics agent and unlock its capabilities with Model Context Protocol.

Learn how to build an Azure AI Foundry Agent that leverages MCP. In this session we will be using the Foundry Agents Service to build a sales data analytics agent and unlock its capabilities with Model Context Protocol.

When two AI agents need to coordinate—share context, delegate subtasks, or merge results—the Model Context Protocol can act as their universal handshake. In this lightning session we’ll show how MCP’s schema, tool catalog, and registry let agents treat each other as remote servers, exchanging capabilities without bespoke glue code.

This session explores the evolving landscape of API Management with remote MCP servers. We'll detail the latest capabilities offered in API Management for exposing and managing these remote servers. Furthermore, discover how to construct your own MCP registry, enabling your developer or agents to leverage a centralized source for MCP server discovery. The session will highlight Azure API Center's role as a private MCP registry, covering its features and current offerings for comprehensive API governance and discovery in this new paradigm.

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.