MCP Dev Summit North America

AI agents are quickly becoming the new browsers, changing how users consume content and get work done. That shift is increasingly powered by a new generation of agentic apps that don’t just present text but deliver interactive experiences within any MCP host. By standardizing interactive UI on MCP, the MCP Apps official extension (SEP-1865) is poised to become the new agentic app runtime, serving as the backbone of the future and removing adoption obstacles that previously hindered the protocol.

Join us to learn more about:

The new web -
How MCP Apps reshapes the traditional app landscape and transforms the way users interact with the web

MCP Apps -
- Architecture
- Real-world use cases
- What's ahead?
- Getting started (+community and #mcp-apps-wg)

Future vision

• Large language models excel at navigating information spread across files, tools, and systems. They can grep, synthesize, and reason about what to look for in response to user prompts. And while this capability improves, a different constraint is emerging: semantic alignment.
• This talk focuses on the premise of context engines. These are systems that encode how an organization’s knowledge is structured and interpreted. In many companies, a term like “customer,” “account,” or “environment” means different things depending on the team or workflow. A context engine captures those relationships and semantics, making them usable both for search and as structured context for LLMs.
• Unlike naive RAG approaches that retrieve documents, context engines provide meaning. They help LLMs interpret intent, disambiguate internal terminology, and reason within the mental model of a specific organization or domain. The same semantic layer that improves search also improves prompting, tool selection, and response quality.
• We’ll explore why the “C” in MCP matters more than ever, how context engines complement modern LLM workflows, and what it looks like to move beyond tools toward shared, durable context.

Layering and connecting multiple MCP systems

Today, there are tens of thousands of MCP servers available, and developers are increasingly pulling unvetted servers from the open internet. While this accelerates experimentation, it also introduces real security risks, leaving enterprises flying blind, with limited visibility into what’s being used and increased exposure to emerging threats such as tool poisoning and prompt injection.
For MCP to scale effectively in enterprise environments, organizations must strike a balance between developer velocity and enterprise-grade visibility and control. A key enabler is a gateway that acts as a unified control plane across MCP servers, clients, and teams.
In this talk, we’ll explore why a gateway is foundational to enterprise MCP adoption and how it enables centralized visibility, secure data flow management, and policy enforcement to mitigate security risks. We’ll also share practical guidance on evaluating MCP gateway solutions including what capabilities matter most, how to choose a solution that fits your needs today, and how to ensure it can scale as MCP adoption grows.

Natural language is becoming a universal interface. Connecting that interface to enterprise systems requires more than protocols. It requires active, thoughtful, and sustained work.

This talk shares Nordstrom's journey enabling MCP and AI agents across the organization: building secure MCP server standards, navigating OAuth and token management for agent workflows, and creating governance frameworks that let teams experiment while ensuring supportability. We'll cover practical challenges and solutions that make the C in MCP reliable, accurate and secure: knowledge feedback loops, layered access management, and evaluation techniques that make "one-to-many" enablement possible.

Beyond the technical, we'll also touch on the human systems work: coordinating across teams when AI initiatives emerge organically, building documentation that drives the right patterns from the start, and patiently creating the organizational foundations that let others follow and build on what you've started.

Most enterprise AI experiences break down at the system boundary, where users know what they need but not which application, process, or data is required to complete it. This session uses procurement as a practical example of a different pattern: a single conversational interface powered by MCP that hides backend complexity while orchestrating work across multiple systems. We’ll show how MCP supports both skills orchestration and enterprise integration, enabling flows such as request classification, requisition creation, status lookup, and intelligent routing between procurement systems. The result is a practical blueprint for scaling system-agnostic workflows across ERP and other back-office functions.

Last year, we spoke about our adoption of Model Context Protocol (MCP) as a foundation for interoperable AI agents and tools at Bloomberg. What we’ve learned since then is that interoperability is the easy part; building trustworthy and interoperable AI infrastructure is the hard part.

Today, MCP powers Bloomberg’s flagship agentic AI solution (ASKB), underpins the experience the firm’s engineers have with our AI development platform, and drives production workflows across Bloomberg. Scaling all of this required more than standardizing tool calls.

In this update, we’ll share how our approach to building trustworthy agentic AI infrastructure down to its core: interceptors to constrain & guide agentic behavior, tool variants to support different models and surfaces, and governance strong enough to let teams innovate quickly without compromising control. Interoperability may get your AI agents connected, but trustworthiness is what enables your agentic AI systems to scale.