MCP Dev Summit North America

What if your AI agent could build and refine its own MCP server while you watch? We'll demonstrate a live development loop where coding agents iterate on MCP servers and UI widgets in real time . no restarts, no broken workflows. Using hot module reloading for both the protocol primitives and the UI, agents can preview and refine their output in real time.



In order to facilitate networking and business relationships at the event, you may choose to visit a third party's booth or access sponsored content. You are never required to visit third party booths or to access sponsored content. When visiting a booth or participating in sponsored activities, the third party will receive some of your registration data. This data includes your first name, last name, title, company, address, email, standard demographics questions (i.e. job function, industry), consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies. 

MCP is poised to be the connective tissue between large‑language models and the data they need. Despite this, many teams still stall at the prototype stage. This talk distills what actually works in production, what still breaks, and why.

I’ll share some lessons building FastMCP, the framework used to build 70% of MCP servers across all languages. We’ll look at the real environments where MCP is thriving, the hurdles teams hit when they move to productize it. Finally, we’ll share a view of the road ahead as context becomes a first‑class product surface.



In order to facilitate networking and business relationships at the event, you may choose to visit a third party's booth or access sponsored content. You are never required to visit third party booths or to access sponsored content. When visiting a booth or participating in sponsored activities, the third party will receive some of your registration data. This data includes your first name, last name, title, company, address, email, standard demographics questions (i.e. job function, industry), consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies. 

When an AI agent holds your OAuth token, what stops it from acting beyond your intent? We'll cover why OAuth 2.1 alone isn't enough for agentic AI, how the industry is responding (NIST, IETF, major identity vendors), and how to implement delegation that gives agents scoped, auditable, revocable permission to act on behalf of users.

Build, scale, govern, and optimize your agents using Google's ecosystem alongside the Model Context Protocol (MCP). This session will zoom through the complete agent lifecycle. We will vibe-code ADK agents with AntiGravity and it will use skills to access WebMCP. We will then tackle infrastructure, showing you how to effectively scale your usage with remote MCP servers, Google Cloud hosting, and decompose into multi-agent systems with A2A. Finally, we will cover critical governance strategies, highlighting how to manage your MCPs, agents, and API tools securely using Apigee or an OSS stack featuring an MCP-enhanced Envoy proxy.

Enterprises are embracing generative and agentic AI as models evolve faster than ever, creating uncertainty. The Model Context Protocol (MCP) resolves this by standardizing connections between AI and underlying services. We demonstrate how the ability to both consume and build MCP services provides the flexibility to bring all your data to any AI easily.



In order to facilitate networking and business relationships at the event, you may choose to visit a third party's booth or access sponsored content. You are never required to visit third party booths or to access sponsored content. When visiting a booth or participating in sponsored activities, the third party will receive some of your registration data. This data includes your first name, last name, title, company, address, email, standard demographics questions (i.e. job function, industry), consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies. 

You can write a perfect MCP server (clean code, typed schemas, 100% code coverage), yet agent interactions still fail. This is the probabilistic gap: your server is deterministic, but its user (the agent) is stochastic.

Standard “Agent Evals” are often the wrong tool to fix this. They judge the final outcome (was the answer good?), not the process. They struggle to provide useful insights into how the agent understands and uses your MCP server, instead focusing on providing insights into the agent itself.

In this session, we introduce mcpchecker, an open source framework for MCP server evaluations. We will show how to build integration tests specifically for the agent-MCP server interface, allowing you to isolate and debug these interactions.

Stop guessing why agents fail. Learn to test your server’s semantic interface and prove that agents can actually understand it.

Developing MCP servers against the APIs you depend on can feel risky, especially when those servers interact with real-world data in production services. When integrating AI into the enterprise, you're often better off starting in a sandbox, but not all 3rd-party APIs offer sandboxes, let alone MCP-compatible ones. No problem: OpenAPI, Microcks, and Bruno are here to help.


At Naftiko, we've been delivering HTTP and MCP sandboxes for common 3rd-party APIs like GitHub, Jira, Notion, and Figma. Our approach uses OpenAPI specifications published to GitHub, open-source Microcks to deliver mock REST APIs and MCP servers, and Bruno as an HTTP client to explore the sandbox. We'll share how we design OpenAPI specs with use-case-driven, business-aligned examples that can be easily forked and mocked on-premise using Microcks, providing a safer development approach for anyone building with MCP and integrating it into LLMs, copilots, and agentic automation.

Join us for a hands-on, practical journey through how OpenAPI, Microcks, GitHub, and Bruno can help you reduce the risk of AI integration with 3rd-party, and internal APIs.

The Model Context Protocol (MCP) is rapidly emerging as a foundational standard for building agentic AI systems that interact with tools, data sources, and services in a consistent and interoperable way. However, adopting MCP effectively requires more than basic integration—it demands thoughtful design choices around security, scalability, observability, and reliability.

This session presents practical best practices for implementing MCP in real-world agentic AI applications. It covers how to structure MCP servers and tools, manage context boundaries, handle permissions and sensitive data, and design resilient agent workflows. The talk also explores patterns for prompt engineering, tool invocation, state management, and error handling when using MCP in cloud-native environments.

Attendees will leave with concrete guidance on how to use MCP to move from experimental agents to production-ready systems that are secure, maintainable, and scalable.

As MCP adoption grows, power users are connecting multiple servers for various workloads. This creates a challenge: in naive implementations, preloading all tool and resource definitions into the context window can add 50k+ tokens before the agent even starts working. Evaluating our agentic coding users at Warp, we found that ~90% of tasks don't use the MCP context available, and those that do only use few tools.

This led us to question whether MCP context needs to be statically front-loaded. So, we built a model-agnostic MCP search subagent that reduces token usage by 26% for MCP-using tasks and 10% when MCP context is available but unused. All in a model-agnostic implementation.

Attendees will leave with:
• A concrete architecture for dynamic MCP tool/resource discovery
• Evaluation strategies for ensuring search doesn't degrade agent quality
• A look into our model-agnostic implementation to adopt in any agentic coding harness