O'Reilly Demo Day

We’re moving from a world of custom integrations and proprietary APIs to a standardized protocol that treats data connectivity as infrastructure. Every application becomes a potential collaborator in a larger AI ecosystem rather than a collection of isolated tools requiring custom integration work.

This is big stuff, and to demonstrate how MCP is creating the architecture of participation for AI systems, we’ve curated a series of really compelling, fast-paced demos from members of our network of experts who are already building proof-of-concept applications on the bleeding edge of MCP. We’re calling this event O’Reilly Demo Day, and we’d love for you to attend.

First, Google’s Heiko Hotz and Sokratis Kartakis will demo how the interplay between Agent2Agent (A2A) communication and MCP creates a powerful foundation where specialized agents can be dynamically discovered and safely execute tools on behalf of other agents, all while maintaining clear boundaries and security controls through standardized protocols.

Then Quantmate’s Nicole Koenigstein will show how autonomous agents can use MCP not just to connect with tools but to communicate with each other. She’ll demo a multi-agent coding system where agents collaborate by sharing, correcting, and evolving code together, using MCP as a shared protocol between reasoning agents, enabling structured coordination, reflection, and continuous innovation. It’s a step toward building self-improving AI systems.

Next, DreamFactory's Jason Gilmore will demonstrate how DreamFactory is using MCP as an entirely new way to introduce its product to key decision makers without requiring them to step through a laborious, time-consuming on-premises installation and database requisition process. Jason believes MCP will ultimately pave the way for a new kind of app store, and he’ll introduce a few steps your organization can take today to put your product in front of more prospective customers than ever before.

After that, PagerDuty’s José Côrte-Real will show how his team built a supervisor-style coordinator agent that asks PagerDuty’s agents real-world questions about analytics and shift scheduling, detecting conflicts, and even creating overrides. Jose will discuss two complementary paths they’re pursuing: first-party agents that offer tight integration and low latency, and MCP-based agents that expose APIs and workflows more flexibly. If you’ve ever wrestled with coordinating multiple AI agents—or wondered how to balance autonomy, performance, and extensibility—you won't want to miss this session.

And then to wrap things up, Flipkart’s Virender Bhargav introduces us to an innovative root cause analysis (RCA) and insights copilot designed to help teams move beyond reactive measures by proactively identifying business anomalies and patterns. Can this agent really reduce anomaly detection time from days to hours, cut mean RCA time to under three hours, and improve coverage of previously undetected incidents by 50%? The proof will be in the pudding!

We think that after you see these demos, you’ll agree that the world has shifted from AI simply being an add-on feature to an existing product to AI as integrated infrastructure that enhances every aspect of how we work with information. MCP enables the kind of network effects that made the web so powerful, in how every new MCP-compatible tool increases the value of every other tool in the ecosystem. We hope you’ll join us for Demo Day and get inspired to make your own tools and connections.

Recommended Resources

• Read AI Agents with MCP (early release book)
• Read Building Applications with AI Agents (early release book)
• Explore MCP Complete Guide – Build and Connect Tools for LLMs (on-demand course)