AGNTCon + MCPCon Japan 2026

___________________________
Presentation Language: English

___________________________
Presentation Language: English

David will discuss the need for connectivity in an era of increasing AI capabilities. Open standards like MCP are at the heart of the AI revolution and the increased ability of models to reach out into the world. We discuss the last two years of MCP and look into the future of connectivity standards in the industry.
___________________________
Presentation Language: English

AI agents are rapidly evolving from chatbots into autonomous systems that use tools, collaborate with other agents, and interact with enterprise data. But as their capabilities grow, so do the operational challenges. How do you know which agent consumed your AI tokens? Which tools were invoked? How do you govern, secure, and observe agent behavior across an increasingly complex ecosystem?

In this demo-driven keynote, Lin invites the audience to become part of a live agent experience, where her AI agent orchestrates multiple services and MCP tools to transform the audience in an unexpected way. Throughout the demo, every request flows through agentgateway, showcasing how an AI gateway enables secure access to MCP servers, intelligent traffic mediation, policy enforcement, cost attribution, and end-to-end observability for production-ready agentic systems.

___________________________
Presentation Language: English

As organizations build more capable agents, those agents will need a common way to communicate and work together across frameworks, vendors, and platforms. This keynote examines the current state of A2A, the problems it is designed to solve, and where the project is headed. We'll also see A2A in action through a production multi-agent system, including what happens when one of its agents is compromised.

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

___________________________
Presentation Language: English

Japan is rapidly embracing Agentic AI. New products, services, and platforms are emerging as organizations explore how AI agents can transform the way we work and build software.

Yet an important question remains:

Who is building the technologies that define the future of AI agents?

Behind every protocol, specification, and open source project is a community shaping how agents communicate, collaborate, authenticate, authorize, and make decisions. These communities are defining the foundations of the Agentic AI ecosystem.

While participation in upstream communities continues to grow worldwide, Japan's presence in the development of the standards and infrastructure behind this ecosystem remains limited.

As AI agents become more widely adopted, adoption alone is not enough. Open source projects and standards bodies are determining how the ecosystem evolves, and participation in these communities allows organizations and individuals to help shape that future.

The future of Agentic AI is being built today through open source projects, technical standards, and the communities behind them.

Will Japan remain a consumer of that future, or become a contributor to it?

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

AI models and agent frameworks are advancing rapidly, but intelligence alone does not make an organisation agentic. To create real value, agents must safely interact with enterprise systems, data, people and business processes.

This keynote explores the architectural challenge beyond the model: building a control and execution layer for enterprise AI. MCP is an important step toward interoperable agent-to-tool interaction, but production systems also require identity, least-privilege access, policy enforcement, human approvals, orchestration, observability and auditability.

The session will offer a practical framework for thinking about how open protocols and agent systems can move from impressive demonstrations to trusted, scalable enterprise action. The central question is not whether an agent can use a tool, but whether an enterprise can safely allow it to do meaningful work.

___________________________
Presentation Language: English

Tool descriptions tell an agent what a tool can do, but not how to orchestrate those capabilities toward a goal, or supplement them with specialized knowledge. Agent skills have become a popular and accessible way to close that gap, and many organizations now ship skills alongside their servers. The community effort to standardize that pairing has drawn 50+ contributors from 25+ organizations across the entire AI infrastructure stack: cloud platforms, data platforms, enterprise SaaS, gateways, and independent implementers. This talk covers where that momentum is headed, and how Extensions let the protocol evolve to meet real-world demand while balancing the stability, security, and developer experience that production systems require.

___________________________
Presentation Language: English