The San Francisco Java User Group

How MCP Bridges LLMs and Data Streams + Post-Mortem Crash Analysis with jcmd

Wed, Apr 8 · 6:00 PM PDT

Workato HQ, 600 Illinois Street, San Francisco, CA, US

The event is a joint effort between the San Francisco JUG and East Bay JUG. ⚠️ RSVP via https://lu.ma/sfjava.

​​​​On this evening, we are excited to hand the mic to Viktor Gamov – a Java Champion from New York City – and Fairoz Matte – a long-time Java developer working on the OpenJDK at Oracle and recent resident of California.

Currently we are still reaching out to hosts. If you want to host us on that day please reach out via this Google form.

⚠️ CAUTION FOR RSVP → WE TRANSITION TO LUMA

All event RSVPS happen on https://lu.ma/sfjava. Please sign up there!
This event is found at: https://luma.com/syopp7c2

​CALL FOR SUPPORT

• Subscribe to our videos
• Join our monthly newsletter
• Join our team
• Submit your talk
• Sponsor or host us

​SCHEDULE

• 5:45 PM Doors Open
• 6:05 PM Intro by the JUG
• ​6:15 PM Talk by Viktor Gamov
• ​7:05 PM Talk by Fairoz Matte

​​Feel free to gather at a bar next door afterwards

• ​​Third Rail https://maps.app.goo.gl/2Jw85hgNDeWYZfsU9
• ​​Sea Star https://maps.app.goo.gl/dEFkeSKefn1patdm7

SESSIONS​

• The Missing Protocol: How MCP Bridges LLMs and Data Streams by Viktor Gamov
• Post-Mortem Crash Analysis with jcmd by Fairoz Matte

​ABSTRACTS

The Missing Protocol: How MCP Bridges LLMs and Data Streams

​Nobody’s talking about this: MCP isn’t just another way to build chatbots. It’s the bridge we’ve been missing between AI reasoning and real-time data systems. Teams build AI applications that work great in demos but fall apart with production data. Your agents analyze historical reports but can’t tell what’s happening in your Kafka streams. They’re blind to schema changes and disconnected from events that matter to your business. Instead of treating streaming platforms like black boxes, you expose them directly to your agents via MCP protocol. Suddenly, your AI doesn’t just read about data—it lives inside your data flows. Learn what becomes possible when you stop thinking about AI as an external service and start treating it as part of your streaming architecture. We’ll build systems where agents subscribe to real-time events, reason about evolving schemas, and make decisions that ripple through your data platform.

Resources

​• Spring AI Kafka Event Summarizer for Confluenct MCP https://github.com/gAmUssA/spring-ai-confluent-mcp
• MCP Confluent Server https://github.com/confluentinc/mcp-confluent
• Spring AI Docs https://docs.spring.io/spring-ai/reference/

Viktor Gamov

Viktor Gamov is a Principal Developer Advocate at Confluent, founded by the original creators of Apache Kafka®. With a rich background in implementing and advocating for distributed systems and cloud-native architectures, Viktor excels in open-source technologies. He is passionate about assisting architects, developers, and operators in crafting systems that are not only low in latency and scalable but also highly available. As a Java Champion and an esteemed speaker, Viktor is known for his insightful presentations at top industry events like JavaOne, Devoxx, Kafka Summit, and QCon. His expertise spans distributed systems, real-time data streaming, JVM, and DevOps.
https://www.linkedin.com/in/vikgamov/ https://www.youtube.com/c/ViktorGamov
https://gamov.io/
https://speaking.gamov.io/

Post-Mortem Crash Analysis with jcmd

This session will surface progress JEP 528 which brings core and minidump support to jcmd. The jcmd tool supports the monitoring and troubleshooting of a running HotSpot JVM. JEP 528 will extend jcmd so that it can also be used to diagnose a JVM that has crashed. This will establish a consistent experience in both live and post-mortem environments.

Fairoz Matte

Fairoz Matte is part of the Java platform team, working in a sustaining group. Mostly involved in community triaging and handling customer bugs. He is esp. a frequent speakers at JUG Bangalore and also a familiar speaker at other developer events like JavaOne. In the past he has also served as a co-organizer of the Bangalore JUG. Recently migrated to Bay area and planning to contribute more towards local JUGs.

https://www.linkedin.com/in/fairoz-matte-74732b63/