MCP Dev Summit Seoul 2026

Despite growing investment in AI, most enterprises still struggle to convert adoption into measurable business results. This session breaks down the structural root causes behind that execution gap and the operational risks created as AI agents proliferate across the organization. We'll then introduce Enterprise MCP, a governance and control framework built for enterprise-level AI oversight, covering how to design performance measurement systems and take a practical approach to agent-based automation that scales safely.

Connecting AI agents and exchanging data is only the first step toward enterprise adoption. True interoperability requires common approaches for identity, authorization, governance, observability, and communication across heterogeneous systems built by different vendors.
This keynote explores the broader industry challenge of building interoperable agent ecosystems and presents AWS’s experience supporting multi-agent collaboration across both the Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication models. The session will discuss architectural patterns and enterprise considerations for enabling secure, scalable, and interoperable AI agents built on open standards, while sharing practical lessons learned from real-world deployments.
Attendees will gain practical insights into the future of interoperable AI agent infrastructure, the role of open standards in accelerating enterprise AI adoption, and the architectural foundations needed to build secure, scalable, and production-ready agent ecosystems.

Video intelligence is an unusual MCP workload. Operations are asynchronous and long-running (indexing a 30-minute video takes minutes, not milliseconds), inputs span local files and remote URLs, and the tool surface is wide; search, analysis, embeddings, and entity recognition each carry distinct parameter shapes and response patterns.

When we set out to build a production MCP server for TwelveLabs' video understanding platform, these constraints became a useful stress test for the protocol itself. This talk traces the builder's journey from first commit to published npm package (twelvelabs-mcp), covering the decisions that shaped a 19-tool MCP server and the patterns that emerged along the way.

Attendees will leave with concrete patterns for building MCP servers around API-first platforms (particularly those with async workflows, multimodal inputs, and wide tool surfaces), along with a clear picture of how MCP servers can evolve into full agent plugins.

MCP has solved a critical problem: giving AI agents access to external tools and data. But access alone isn't enough. An agent with a database tool can still write terrible queries. An agent with a deployment tool can still push unsafe changes. The gap isn't access. It's expertise. Agent Skills are a lightweight format for encoding the domain knowledge agents need to use tools well. A common misconception is that Skills replace MCP. They don't. MCP provides capabilities: live connections to real systems. Skills provide knowledge: patterns to follow, mistakes to avoid, conventions a team considers non-negotiable. Skills ensure an agent does things right. MCP ensures it does real things. You need both. In this talk, I'll show how they work together through real examples. You'll see agents that call tools with the right arguments, handle edge cases, and recover from errors like an experienced developer would. As the creator of Apollo MCP Server and Apollo Skills, I've built on both sides of this equation and will share the challenges of shipping both: distributing them together, keeping them in sync, and evaluating if they still add value as models get smarter.

Six months ago, building a voice AI agent on our platform meant clicking through a UI. This meant editing prompts, dragging conversation flows, hooking up tools with no audit, no rollback, no review. To make the platform work better with MCP, we moved everything to a Git-backed harness. Each agent is now its own repo with skill folders and an agent.md capturing the agent's custom instructions and unique nuances, so when a customer points Cursor or Claude at it via MCP, the AI picks up that context before making any changes.

This talk covers:
(1) the org-change journey from clickops to version control
(2) the sandboxing model, how MCP safely exposes Git's branch model (dual read/write endpoints, tool-layer branch protection, SSO-derived org scoping)
(3) the two-stage CI on every PR, MCP-driven changes ride the same rails as human-authored ones, with simulations followed by automated evaluations
(4) the closed-loop flow that ties it all together, a user files an issue with a test scenario on an agent's page, the sandboxed AI makes the change, validates it, and submits a PR for review using MCP.

Most MCP systems today are static at runtime. We define tools, expose schemas and rely on prompts to guide behavior, then hope the system remains reliable after deployment.

In practice, MCP-based systems drift. Agents repeatedly misuse tools, call inefficient sequences or fail in predictable ways. Tool descriptions become outdated. Context grows noisy. Human operators step in to correct outcomes, but those corrections are rarely captured or reused. MCP standardizes how agents connect to tools, but it does not define how systems improve over time.

I would like to explore how to build MCP systems that go beyond execution by introducing feedback loops on top of the protocol. By combining tool call history and observability, we can build systems that identify their own weaknesses and suggest improvements safely.

The session will cover practical patterns:
- Detecting repeated tool misuse and failure patterns
- Learning from retries, fallbacks, and human corrections
- Identifying redundant or low-value tool chains
- Designing safe feedback loops with audit logs, versioning, rollback and human approval

As the ecosystem for the Model Context Protocol (MCP) expands, developers are hitting a familiar wall: token bloat. While MCP provides a powerful standardized interface for LLMs to interact with external data, the "context tax" of verbose tool definitions and massive data payloads can quickly degrade performance and spike costs. To build production-ready agents, we must move beyond basic implementations and embrace advanced orchestration.

This session dives into the architecture of efficient MCP server design, focusing on the "Code Mode" technique. We will explore how to shift the heavy lifting from the LLM’s reasoning space to the server’s execution environment. Instead of forcing the model to process raw, unrefined data, "Code Mode" empowers the LLM to generate and ship logic—miniature, execution-ready scripts—directly to the MCP server. This approach minimizes round-trip latency and drastically reduces the input tokens required for complex data manipulation.