Blog: | Tim Berglund is back at the lightboard with *MCP* (Model Context Protocol). MCP really _is_ a big deal, but most people are missing the point. It's not just about enhancing desktop applications with agentic functionality—it's about exposing reusable tools and resources (including real-time data from sources like Apache Kafka) to build _agentic microservices._ Doing this takes us beyond basic LLM chatbots to dynamic, problem-solving systems that deliver real value in real professional settings. LEARN MORE ► Blog: Powering AI Agents with MCP & Confluent: ► GitHub: Confluent MCP Server: ► Webinar on MCP & Confluent: ► Confluent Developer: CHAPTERS 00:00 - The need for broader vision with Model Context Protocol (MCP) and agentic AI applications 01:30 - How LLMs work and their limitations in taking actions 03:00 - The importance of tools and resources for agentic behavior 04:30 - MCP architecture: Host app, client library, and server 06:30 - Example: Building an agentic appointment scheduling app 09:00 - Workflow: Prompting, accessing resources, and invoking tools CONNECT Subscribe, if you dare: @ConfluentDeveloper?sub_confirmation=1 Community Slack: X: Linkedin: GitHub: Site: ABOUT CONFLUENT DEVELOPER Confluent Developer provides comprehensive resources for developers looking to learn about Apache Kafka®, Apache Flink®, Confluent Cloud, Confluent Platform, and any other technology related to the broader Data Streaming Platform. Content on Confluent Developer includes courses, getting started guides, topical deep-dives, patterns, tutorials, and listings of community events. Learn more at . #modelcontextprotocol #confluent #apachekafka