AI Agents Meet the New MCP

This talk presents Quarkus MCP Server 2.0 aligned with the major new MCP specification, now stateless and session-free. It shows how to build a Quarkus MCP server and connect it to a LangChain4j-powered AI agent that discovers tools at runtime and chains actions across enterprise systems.

talk.summaryAiDisclaimer

Zineb BendhibaApache Camel

talks.description

The Model Context Protocol (MCP) quickly established itself as the open standard for connecting AI to enterprise systems. The 2026-07-28 specification introduces its largest revision. The protocol moves to a stateless core, removes sessions, and introduces new mechanisms for server-client interactions.

Quarkus MCP Server 2.0 fully embraces the new specification. In this talk, I will show how to build a Quarkus MCP server aligned with the latest protocol, and connect it to an AI agent powered by LangChain4j. Through live demos, you'll see an agent discover MCP tools at runtime, chain actions across enterprise systems, and act on the results. All through Quarkus.

Join me to explore how the new MCP, combined with Quarkus and LangChain4j, takes us from connecting AI to enterprise systems to building agents that act autonomously!

mcp

quarkus

langchain4j

enterprise

talks.speakers

Zineb Bendhiba

Apache Camel

France

Hi, I'm Zineb Bendhiba. I love building things that solve real problems for users. Principal Software Engineer, working on Enterprise Integration. Right now I'm focused on bringing AI into the open source projects I contribute to. Apache Camel PMC member, Camel Quarkus and Quarkus Qdrant maintainer. I also contribute to Quarkus, Wanaku, and Kaoto. Open source, conferences, and dancing.
Full bio: https://zinebbendhiba.com/bio/