MCP Dev Summit North America

At HubSpot, we recognized that any RPC with a schema is already a tool definition, so we built our AI tooling infrastructure on top of our existing RPC framework instead of starting from scratch. Engineering teams can now expose any API to internal agents, public MCP clients, and customer-facing AI products with just two annotations, enabling rapid development and tool reuse across all of our AI systems. This talk covers the architecture, the tradeoffs, and how this approach let us ship agentic capabilities faster than we ever expected.

As MCP adoption grows, teams quickly discover that scaling from a single MCP server to a multi-server ecosystem introduces new architectural, operational, and governance challenges. Patterns that work for standalone MCP implementations often break down when MCP becomes a shared platform capability across multiple domains, teams, and clients.

In this talk, we share practical lessons from building and operating an MCP server ecosystem at infrastructure scale at Equinix. What began as a single MCP server evolved into multiple coordinated MCP servers spanning networking and infrastructure domains, each with distinct tools, lifecycles, and operational constraints.

Attendees will learn:
1. How MCP architecture changes when scaling from one server to an ecosystem
2. Design patterns to avoid tight coupling and fragmentation across MCP servers
3. Practical approaches to tool discovery, versioning, and backward compatibility
4. Operational lessons for reliability, rate limiting, and failure isolation
5. Governance best practices for ownership, change management, and ecosystem growth

Delivering unstructured file content over MCP introduces various challenges in performance, efficiency, and security. We will explore the questions that arise when building an MCP server for content management and some of the approaches that can be used to tackle them. As enterprise environments require a more conservative security posture, we’ll also break down strategies for mitigating data exfiltration risks and prompt injection attacks through granular, configurable guardrails.

• Why large content operations can fail: latency, data corruption
• Techniques for managing context efficiently and minimizing LLM token usage
• The benefits of programmatic tool calling for MCP tool composability
• Tradeoffs between MCP and CLI for content operations
• Handling safety risks when untrusted content becomes a data exfiltration vector
• Balancing functionality and security when designing tool guardrails

By starting from first principles and reviewing specific examples attendees will leave with techniques for building MCP servers that process unstructured content efficiently and securely in enterprise environments.

As MCP adoption grows, a challenge emerges: how do you expose 100’s of tools from a single server without overwhelming agent context windows? This talk introduces an MCP tool discovery mechanism we’ve built that dynamically loads tools. The platform works with a single discovery meta-tool on initialization, server-side state management to track agent context, and leveraging streamed MCP’s notifications/tools/list_changed to push relevant tool sets mid-session. Agents declare their problem context (incident response, monitoring etc) and receive only the tools they need, when they need them. Attendees will learn how this pattern keeps context windows lean while maintaining access to a broad tool ecosystem, with real examples showing how a single MCP server can serve diverse agent use cases without tool overload.

When the backend can reason, what does that mean for the frontend? Let's look at how to build UIs that support reasoning and adapt to any task.

The way we interact with software is changing. LLM-powered applications, with human-in-the-loop, are handling repetitive tasks that used to require forms and workflows. But bolting a chatbot onto your existing UI isn't enough - extracting structured data from natural language is fragile, adding frustration and friction for users.

In this talk, we'll explore how tool-calling and protocols like MCP provide deterministic contracts with non-deterministic systems, what human-in-the-loop looks like when the UI adapts to the task at hand rather than forcing users through fixed workflows.

Healthcare providers lose 30-60 minutes per insurance claim error, with the industry wasting $250B+ annually on administrative overhead. At Kustode, we built a multi-tenant RCM platform processing thousands of daily EDI transactions (837P claims, 835 remittances, 270/271 eligibility). While we automated the EDI pipes, intelligent workflow orchestration—denial management, prior authorization, claim intervention—remained manual until we integrated MCP.
You'll learn:
- Integrating MCP into existing production systems vs. greenfield builds
- Multi-tenant MCP architecture with PHI isolation and compliance
- Orchestrating long-running workflows (45+ day denial cycles) with state management
- Real workflows: automated denial resolution, prior auth orchestration, intelligent claim intervention
- Security patterns for MCP in regulated environments
- Production metrics: time savings, denial reduction, deployment challenges
- When MCP beats traditional API orchestration
This talk shares production lessons from deploying MCP workflows in a HIPAA-compliant healthcare platform

Now live on GitHub, gcloud-mcp is the open-source reference implementation bringing agentic power to Google Cloud via the Model Context Protocol. As cloud platforms grow more complex, traditional CLIs struggle to support exploratory, goal-driven interactions. This session shares architectural lessons from building the bridge between AI assistants and enterprise cloud services to enable agent-driven reasoning.

Using the Storage MCP server as a deep dive, we demonstrate how AI assistants interact with Google Cloud Storage via MCP. We’ll show how raw GCS APIs were transformed into high-level Storage Intelligence tools that support meaningful workflows rather than simple command execution.

We focus on the design of the /storage-mcp package, including how we summarize GCS metadata into concise, accurate responses that agents can reason over without hitting context limits. Finally, we discuss how metrics like cost, latency, and task accuracy guided our iteration, helping refine prompt design and tool granularity. Attendees will leave with practical, enterprise-ready patterns for building local MCP servers that enable efficient interaction with complex cloud infrastructure.