As enterprises across Japan move AI agents into systems their businesses depend on, the questions get harder including where to draw trust boundaries when multiple agents interact, how to enforce approval gates and audit trails, and how to verify an agent’s output. The AGNTCon + MCPCon Japan program was built around these questions, with more than 40 sessions providing real world evidence, honest trade offs, and lessons practitioners can put to work immediately. <\/p>\n “The rapid adoption of open agent frameworks and protocols across Japan underscores a clear demand for reliable, secure, and interoperable AI systems,” said Mazin Gilbert, Executive Director of the Agentic AI Foundation. “As developers move from experimental prototypes to mission-critical systems, this conference showcases the hard technical work happening across Asia-Pacific, from tool integration and sandboxing to multi-agent coordination, evaluation and enterprise governance.” <\/p>\n Highlights at AGNTCon + MCPCon Japan 2026 include: <\/p>\n Designing Trustworthy Agent Systems <\/p>\n As agentic systems move closer to enterprise data, internal tools, and operational workflows, teams need clear boundaries for what agents can access, who controls decisions, and where governance should be enforced. Explore practical approaches to trust, oversight, and control in multi-agent environments. <\/p>\n Story continues <\/p>\n Session highlight:\u00a0Designing Trust Boundaries for Agent-to-Agent Systems: Lessons Learned from a Technical PoC \u2013 Ryuji Iijima, SoftBank Corp.<\/a> <\/p>\n Building the Open Agentic Stack <\/p>\n Agentic AI requires more than a single framework. Teams are combining open source components, orchestration layers, authentication systems, observability tools, and emerging multi-agent patterns into complete architectures. Learn how leading engineering teams navigate open source integration to build complete, production-ready agent platforms. <\/p>\n Session highlight: What’s Missing in the Open Agentic Stack: Lessons From OSS Integration \u2013 Tatsuya Sato & Satoshi Ito, Hitachi, Ltd.<\/a> <\/p>\n Evaluating Agents Before Production <\/p>\n As agents become more autonomous, traditional testing approaches are not enough. Teams need ways to evaluate routing behavior, tool use, prompt changes, regressions, and edge cases before systems reach production. Explore practical methods for making agent behavior more measurable, repeatable, and safe to deploy. <\/p>\n Session highlight: From Clicks To Context: Building an Open-Source Evaluation Pipeline for AI Agents – In\u00eas Bola\u00f1os, PagerDuty<\/a> <\/p>\n Sessions span nine tracks including Building Reliable Agent Systems, Multi-Agent and Distributed Systems, Agentic Engineering, and Interoperability, Protocols & Standards, with speakers from companies including Adobe, Anthropic, Google, IBM, JP Morgan Chase, Microsoft, Red Hat, Uber, and Walmart Global Tech, alongside Japan’s open source and AI engineering community including Hitachi, SoftBank, and NTT. <\/p>\n MCPCon, the conference’s dedicated MCP track, offers protocol builders and tool developers deep coverage of the fast-moving MCP ecosystem, including authorization and identity, the latest transport and task lifecycle specifications, running MCP infrastructure at scale, and a keynote by the protocol’s co-creator, David Soria Parra, Member of Technical Staff at Anthropic. <\/p>\n To view the complete schedule for AGNTCon + MCPCon Japan 2026, visit: events.linuxfoundation.org\/agntcon-mcpcon-japan\/program\/schedule\/<\/a> <\/p>\n Certification & Hands-On Opportunities Registration Sponsorship Platinum Sponsor: Hitachi <\/p>\n Gold Sponsor: Akamai, Auth0 by Okta, Neo4j, StepFun <\/p>\n To learn more about becoming an event sponsor,\u00a0click here<\/a>. <\/p>\n About the Agentic AI Foundation Media Contact<\/a> AAIF logo <\/p>\n
Attendees will also have discounted access to dedicated pathways for the Model Context Protocol Associate (MCPA) Certification<\/a>, providing developers and architects with structured opportunities to validate technical proficiency in MCP standards, tooling, and ecosystem practices. <\/p>\n
Standard registration for\u00a0AGNTCon + MCPCon Japan<\/a>\u00a0is available until Friday, September 11, 23:59 JST. <\/p>\n
AGNTCon + MCPCon Japan 2026 is made possible through industry leaders, including: <\/p>\n
The Agentic AI Foundation (AAIF) is the neutral home where the agentic stack is being built. With founding projects including MCP, goose, AGENTS.md, and agentgateway, AAIF governs the core standards and protocols that enable agents to operate interoperably across platforms. Through transparent governance and broad industry participation, AAIF is driving adoption and ensuring agentic AI infrastructure evolves openly, predictably, and at production scale. For more information, please visit aaif.io<\/a>. <\/p>\n
Sarah Zonouzi
Agentic AI Foundation
pr@aaif.io<\/a> <\/p>\n