MCP Dev Summit North America

The job of a software engineer is rapidly evolving. We're now beyond using AI as a Stack Overflow alternative or even as a pair programmer. Agentic engineering - the act of building and maintaining a system to reliably give coding agents the tools and context they need to complete work autonomously - is the new layer of abstraction the industry is moving toward.

Core to building these autonomous coding agents is the notion of a "closed agentic loop". To create a closed loop for your coding agent, you need to provide it (1) tools to verify work is complete, (2) tools to debug work along the way, and (3) a carefully crafted prompt that communicates a "definition of done" that pulls it all together. That empowers your agent to iterate on solutions - sometimes for hours - until it delivers to completion.

As you might imagine, MCP is often the ideal delivery mechanism for those loop-closing tools.

In this workshop, we will:
Introduce the concept of agentic engineering and the "aha" moments that can take you from pair programming with a single agent to regularly wielding 5-10 coding agents at once. 

Close a simple loop: Figma design to working, pixel-perfect UI element verified by Playwright.
Close a more complex loop: take an alert from an observability platform, reproduce the problem in a staging environment with Playwright, capture the logs, open a PR with a fix, deploy to staging, verify the fix, and close the alert - all in one prompt.

Encourage you to try building a loop on your own codebase for a real piece of work on your plate - and raise to the group what kind of hurdles you might run into while trying to do so

You'll leave with actionable next steps to make your team's codebase agentic-engineering-ready and a clear picture of what success looks like.

Pre-registration and additional fee is required. To register: add it to your MCP Dev Summit North America registration. 

Enterprise adoption of the Model Context Protocol is accelerating — but the path from "MCP works on my laptop" to "MCP is running securely across our organization" is windy and challenging. The reality is that building MCPs isn’t particularly hard. Instead, the challenges are around OAuth, identity sprawl, and the governance requirements your security team will eventually land on your desk.

The core insight is straightforward: MCP servers should focus on tools, resources, and prompts — not rebuilding OAuth infrastructure from scratch every time. A dedicated identity and governance control plane can absorb that complexity once, rather than forcing every server to solve it independently.

In this workshop, we will:
Break down the authentication challenges blocking enterprise MCP adoption — OAuth scopes, dynamic client registration, token lifecycle management, and why static-only providers like Microsoft Entra are their own special headache

Show how consolidating identity into a control plane changes your architecture from a sprawl of redundant auth implementations into something actually manageable

Work through real governance scenarios: integrating remote MCP servers with an enterprise IdP, scoping tool access by user group, and applying controls at the individual tool level

Look at what central auditing and token revocation give your security team — and why that matters for getting MCP approved for production

Cover filtering strategies for PII exposure and prompt injection on MCP tool calls

You'll leave with a clearer picture of the architectural decisions ahead of you, and a better sense of what your security team is going to ask for before they sign off on any of this.


Pre-registration and additional fee is required. To register: add it to your MCP Dev Summit North America registration.