Skip to main content
🤖 Running agents for a team, not just yourself? Get an independent review of identity, secrets, failover, observability and governance. Assess your agent platform
AGNTCon + MCPCon Europe 2026 official hero graphic showing an abstract connected network of nodes in blue, purple, and pink gradients on a dark navy background
AI

AGNTCon + MCPCon Europe 2026 in Amsterdam

AGNTCon + MCPCon Europe lands September 17-18, 2026 at RAI Amsterdam. Preview of the agentic AI + MCP conference from the people building the stack.

LB
Luca Berton
· 3 min read

Update, September 2026: AGNTCon + MCPCon Europe has wrapped. Read my key takeaways from the two days at RAI Amsterdam — the production lessons that matter now.

I’m an official media partner for AGNTCon + MCPCon Europe 2026, held at RAI Amsterdam on September 17-18. As part of that I get an early look at the program and the people on stage, and the lineup is genuinely the people building this stuff, not just talking about it.

RAI Amsterdam venue ahead of AGNTCon + MCPCon Europe 2026

RAI Amsterdam, the venue for AGNTCon + MCPCon Europe 2026 — Where the agentic stack is being built.

The essentials

  • When: September 17-18, 2026
  • Where: RAI Amsterdam, Netherlands
  • Tagline: Where the agentic stack is being built
  • Focus: Model Context Protocol (MCP) + the broader agent landscape — reliable, scalable, secure agent systems in production
  • Hosted by: The Agentic AI Foundation (under the Linux Foundation events umbrella)

Why this one matters

The agentic stack is moving fast, and most of the hard problems are no longer “can a model do X” — they’re about making agent systems that are reliable, scalable, and secure once they leave a notebook and hit real infrastructure. AGNTCon + MCPCon is where that conversation is happening: core agent architectures, orchestration, observability, the protocols (MCP first among them) that make tools and services interoperable, and the real-world case studies from teams running agents in production.

The audience matches that: open-source contributors building MCP and agentic projects, project maintainers and foundation leaders, enterprise engineers and architects adopting agent-based systems, platform and infrastructure teams supporting orchestration and security, and researchers exploring where agentic systems go next.

Speakers to watch

The confirmed keynotes already read like a who’s-who of the protocol and agentic tooling world:

  • Angie Jones — VP of Developer Experience, The Agentic AI Foundation
  • David Soria Parra — Co-creator of the Model Context Protocol (MCP), Anthropic
  • Clare Liguori — Senior Principal Engineer, AWS (core MCP specification maintainer; Kiro and Strands Agents SDK)
  • Dexter Horthy — CEO & Co-founder, HumanLayer (coined “context engineering”)
  • Idit Levine — Founder & CEO, solo.io
  • Dominic Farolino — Software Engineer, Google (agentic web platform APIs in Chrome)
  • FrĂ©dĂ©ric Barthelet — CTO & Co-founder, Alpic (Skybridge, open-source MCP Apps framework)

Beyond the keynotes, the program is organized into seven technical tracks that map to the full agent lifecycle:

  • Agentic Engineering — harnesses, workflows, agent skills, context and memory design, cost and compute efficiency
  • Building Reliable Agent Systems — architecture patterns, guardrails and sandboxing, observability, production failure modes
  • Evals & Testing — regression suites, evaluation pipelines, release gates for systems that reason and act
  • Human-Agent Collaboration — approval workflows, trust interfaces, keeping humans meaningfully in the loop
  • Interoperability & Standards — agent identity and delegation, access control boundaries, open protocols
  • MCPCon — the MCP 2026-07-28 specification (stateless core, extensions framework, authorization changes), migration strategies, and production lessons
  • Enterprise Adoption in Practice — real case studies, cost management, regulated-industry constraints, organizational patterns
  • Agentic Commerce — the protocols and infrastructure for agents that shop, sell, and pay on behalf of people and businesses

Workshops — no extra fee, included with registration — cover human-agent collaboration in shared workflows, building autonomous coding-agent harnesses, implementing persistent agent memory, securing and routing MCP and LLM traffic through an agent gateway, and governing agent actions across MCP servers, CLIs, Skills, and agent-generated code.

There’s also a Model Context Protocol Associate (MCPA) certification available alongside the event if you want to put a credential next to the hands-on work.

Livestream: free access, 36 hours of content

Can’t make it to Amsterdam? The Agentic AI Foundation ran a dedicated livestream at https://luma.com/av4cbmw8, covering both days continuously. The same keynotes, technical sessions, and closing panel were all streamed — no ticket required.

Recordings are rolling out on the Agentic AI Foundation YouTube channel.


This is a preview — if you weren’t able to join us in Amsterdam, recordings from all sessions are rolling out on the Agentic AI Foundation YouTube channel. In the meantime, the slides and announcements from the event will be linked below as they’re published.

#AGNTCon #MCPCon #Model Context Protocol #Agentic AI #AI Agents #Amsterdam #Linux Foundation #RAI Amsterdam #MCP
Share:
Luca Berton — The Production AI Expert, Docker Captain

Luca Berton

The Production AI Expert · Docker Captain · KubeCon Speaker

15+ years in enterprise infrastructure. Author of 8 technical books, creator of Ansible Pilot (1M+ YouTube views, 648K site users). Former Red Hat engineer. Speaker at KubeCon EU 2026 and Red Hat Summit 2026.

Free 30-min Production AI consultation

Book Now