MCP Dev Summit North America: Full Schedule

April 2-3, 2026
New York, NY
View More Details & Registration

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for MCP Dev Summit North America to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration..

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

11:50am EDT

MCP at 18 Months: Protocols, Patterns, and What We Didn't See Coming - Shaun Smith, Hugging Face

Thursday April 2, 2026 11:50am - 12:15pm EDT

Broadway Ballroom South (6th Floor)

MCP launched a revolution in peoples expectations of what Generative AI could achieve. Since then, MCP has been supplemented by other protocols, techniques and extensions.

At Hugging Face we have 1000s of AI Applications deployed, using MCP for interconnectivity, as well as supporting Remote MCP via Inference Providers.

This experience based session explores how inference, compute and storage workloads are shifting in an agentic world, and how MCP supports us in a rapidly changing environment.

We will:
- Contrast how ACP and Open Responses work within our MCP infrastructure and our experience deploying them.
- Explore how Skills, and Code Generation fit, the impact future models will have on the landscape - and why things that may seem obvious in hindsight weren't.
- Discuss the value of multi-model environments and how subagent patterns are critical for certain tasks.
- Report on the trends we see in shifting Agentic and Inference workloads, and MCPs continued role in supporting them
- Examine our unique multimodal demands - and what needs we and our community have to support mixed content.

Speakers

Shaun Smith

Open Source MCP and Agents, Hugging Face

Shaun Smith leads Open Source MCP at Hugging Face, and is an MCP Steering Committee member serving as a Community Moderator and within the Transports Working Group.

Thursday April 2, 2026 11:50am - 12:15pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

12:20pm EDT

Dynamic MCPs: Agentic Discovery, Configuration, and Management of MCP Workloads - Jim Clark, Docker

Thursday April 2, 2026 12:20pm - 12:45pm EDT

Broadway Ballroom South (6th Floor)

With the rapid expansion of available MCP servers, we need ways to manage our MCP workloads dynamically. Agents can help us configure agents! This talk explores a set of _primordial_ MCP tools that enable agents to discover, configure, and activate MCP servers at runtime. Rather than focusing on deferred tool loading or context reduction, we examine how agents can discover relevant servers from community registries or private catalogs, elicit configuration from users, and activate tools in the current session. We also examine the use of elicitation URLs as a key building block for constructing portable, reusable MCP configurations.

Speakers

Jim Clark

Principal Engineer, Docker

Physics dropout turned software engineer now working on AI Tools and security team at Docker. Spent 25 years building developer tools, including co-founding Atomist (acquired by Docker in 2022). Now containerizing AI agents so they play nicely with humans. Regular conference speaker... Read More →

Thursday April 2, 2026 12:20pm - 12:45pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Any

12:50pm EDT

Building ChatGPT Apps: Principles for a New Kind of Interface - Elliot Garreffa, Ghost Team

Thursday April 2, 2026 12:50pm - 1:15pm EDT

Broadway Ballroom South (6th Floor)

ChatGPT apps aren't websites or mobile apps. They're a new primitive - lightweight tools invoked within a conversation, surfacing minimal UI to move the user forward.

Websites are destinations. Mobile apps are rich installed experiences with device access. ChatGPT apps are in-flow utilities - joining tasks already in progress. You don't own the screen or control the journey. The model decides when to invoke you.

Wrong mental model = wrong architecture.

Drawing on first-hand experience shipping ChatGPT apps for enterprise clients, we'll cover the principles separating apps that work from those that don't:

- Scoping around single, sharp intent vs building a platform inside a chat
- Where conversational interfaces add genuine value - and where you're fighting the medium
- Leveraging context and memory instead of requiring users to re-establish state
- Using ChatGPT as infrastructure vs distribution
- Testing and iterating when the model controls invocation

We'll walk through concrete implementation examples and lessons learned.

Speakers

Elliot Garreffa

Co-founder, Ghost Team

Elliot Garreffa is Co-founder and Head of Growth at Ghost Team, an AI-development studio building AI agents, MCP-Apps and ChatGPT Apps for enterprise B2B SaaS clients. Through his company Ghost Team he has pioneered production-grade MCP implementations for enterprise clients & built... Read More →

Thursday April 2, 2026 12:50pm - 1:15pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices, Apps and Agents

Audience Experience Level Beginner

2:35pm EDT

Mental Reset: How To Rethink Your User Flow in the Age of MCP & ChatGPT Apps - Erica Beavers, Alpic

Thursday April 2, 2026 2:35pm - 3:00pm EDT

Broadway Ballroom South (6th Floor)

Remember when the mobile app stores launched? The first wave of apps were glorified websites, until someone made you tilt your phone to "drink" a virtual beer. That novelty unlocked the iPhone's true potential: apps that felt native to the device. Today, we're at a similar inflection point with ChatGPT Apps and MCP integrations.

After building dozens of AI-powered applications, we’ve identified some interaction patterns that truly shine and those that fall flat.

This talk explores what makes ChatGPT (& MCP) apps fundamentally different from traditional software.

We'll examine novel use cases like adaptive gaming where models seamlessly adopt complex roles, analytics tools that merge interactive visualizations with conversational insights, and SaaS integrations that surface the right features at the right time.

You’ll learn how to design for this new paradigm: what to expose, how users move through AI-native workflows, and what doesn’t work. Your product now lives inside the highest-distribution AI platform. The real question isn’t whether to build for it, but how to make apps that feel truly revolutionary.

Speakers

Erica Beavers

Cofounder, Alpic

Co-founder of Alpic, seasoned infrastructure builders with deep experience in distributed systems, serverless architecture, and developer platforms. Previously, built Streamroot, a video delivery startup acquired by a major US telco, and now focused on making agent-native apps easy... Read More →

Thursday April 2, 2026 2:35pm - 3:00pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

3:05pm EDT

Skills Vs. MCP Vs. Code Mode: Cutting Through the Hype (and the Rage) - Nikolay Rodionov, Alpic

Thursday April 2, 2026 3:05pm - 3:30pm EDT

Broadway Ballroom South (6th Floor)

The AI agent ecosystem is fragmenting into competing paradigms, each promising to be the future of how AI systems interact with the world. Skills are simple markdown local workflows using scripts, MCP provides structured tool access across platforms, and Code Mode solves Context bloat problems by executing MCP Tools as code. Most people think these are competing paradigms. They are not.

This talk cuts through the hype and developer frustration to examine what these approaches actually enable, how they overlap, and how do they complete each other.

**Key Learnings**

- Clear mental model explaining the concepts behind Skills, MCP, and Code Mode: what each actually does vs. marketing claims
- How these paradigms complement rather than compete: practical patterns for combining them (Skills in MCP Servers!)
- Decision framework: when to reach for each approach based on your use case, and a map of in which MCP Client each concept is already implemented
- Where the ecosystem is heading and how to future-proof your architectural choices

Speakers

Nikolay Rodionov

Co-founder and COO, Alpic

Nikolay Rodionov is a cofounder and COO at Alpic, an AI infrastructure startup for MCP, and creator of Skybridge, an open-source framework to build MCP Apps. He previously founded Streamroot, a P2P video delivery technology that powered multiple Super Bowl streaming events before... Read More →

MCP Dev Summit MCP vs Code Mode vs Skills pdf

Thursday April 2, 2026 3:05pm - 3:30pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

3:35pm EDT

Code Mode Is Best Served in the Shell - Jan Curn, Apify

Thursday April 2, 2026 3:35pm - 4:00pm EDT

Broadway Ballroom South (6th Floor)

MCP adoption is growing, but most agent integrations still treat tools as a prompt-time API, burning context tokens on tool definitions, re-copying intermediate results, and losing accuracy along the way. This improper use also leads to unfair criticism of MCP itself.

To address this problem, Cloudflare proposed MCP “code mode”: instead of prompt-time JSON tool calls, the model generates small programs that call tools via an API and run in a sandbox. This dramatically reduces overhead while improving accuracy in chained tool use. An alternative approach recently implemented by Cursor and Anthropic uses dynamic tool discovery to load only the relevant tools into context.

In this talk, we’ll introduce 𝚖𝚌𝚙𝚌 (https://github.com/apify/mcpc), a new open-source universal CLI client for MCP that brings both code mode and dynamic tool discovery to where they shine: the terminal. With persistent sessions, JSON output for scripting, and an MCP proxy for sandboxing, mcpc is an invaluable tool for AI engineers. We’ll live-demo a practical workflow that invokes multiple MCP servers in parallel, filters and transforms results locally, and then turns the interaction into reusable scripts.

Speakers

Jan Curn

Founder & CEO, Apify

Jan Curn is the founder and CEO of Apify (https://apify.com), the world's largest marketplace of web data extraction and automation tools, powering (not only) AI agents with up-to-date data. He has a lifelong passion for software engineering, which earned him an MSc and a PhD in computer... Read More →

2026 04 02 MCP Dev Summit NYC talk pdf

Thursday April 2, 2026 3:35pm - 4:00pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate
Session Slides Yes

4:30pm EDT

Schema To Insight: Architecting Production-Grade Database MCP Tools - Kurtis Van Gent & Wenxin Du, Google

Thursday April 2, 2026 4:30pm - 4:55pm EDT

Broadway Ballroom South (6th Floor)

Connecting an LLM to a database is the "Hello World" of agentic AI, but scaling that to production requires solving complex problems in security, context management, and reliability. You can't simply feed a 500-table schema into a context window and hope for the best.
In this session, the creators of the MCP Toolbox for Databases (12.5k stars) break down the specific architecture required to give agents safe, high-fidelity access to your data. You will learn the patterns that power over 6 million monthly tool calls, including:
Raw SQL vs. Semantic Abstraction: A framework for deciding when to give an agent raw query power vs. when to abstract logic into strict semantic tools.
Safety & Governance: Implementing read-only guardrails, query validation, and "Human-in-the-Loop" friction points to prevent accidental data loss or injection risks.
Reducing Hallucinations: How to format database metadata and column descriptions to drastically improve an agent's query accuracy.

Speakers

Kurtis Van Gent

Senior Staff Software Engineer, Google

Kurtis Van Gent is a MCP Core Maintainer and leads the MCP Transports Working Group. By day, he leads AI Ecosystems + Integrations for Google Cloud Databases and helped create MCP Toolbox for Databases.

Wenxin Du

Software Engineer, Google

Wenxin Du is a core maintainer of MCP Toolbox for Databases. She delivered the end-to-end implementation of Toolbox's end-user authorization system and integrated semantic search functionality into Toolbox.

Thursday April 2, 2026 4:30pm - 4:55pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Advanced

5:00pm EDT

Combine Skills and MCP To Close the Context Gap - Pedro Rodrigues, Supabase

Thursday April 2, 2026 5:00pm - 5:25pm EDT

Broadway Ballroom South (6th Floor)

As AI agents become more capable, their biggest limitation is no longer reasoning — it’s context. Without access to procedural knowledge and domain-specific understanding, agents struggle to perform real work reliably. In this talk, we’ll explore how Skills address this gap by giving agents on-demand access to company-, team-, and user-specific context.

We’ll look at how Skills can be combined with MCP servers to build safer, more reliable agents, and walk through a real-world example of managing a Postgres database. Using evals, we’ll compare agent performance with and without Postgres-specific Skills, showing how MCP enables secure database access while dramatically improving outcomes.

Speakers

Pedro Rodrigues

AI Tooling Engineer, Supabase

I’m an AI Tooling Engineer at Supabase, part of the team maintaining all AI initiatives including our MCP server, AI assistant, and Skills. I’ve been involved with the MCP protocol since its early days, contributing to its SDKs and projects like Skybridge. I’ve spoken at MCP... Read More →

presentation pdf

Thursday April 2, 2026 5:00pm - 5:25pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate
Session Slides Yes

5:30pm EDT

If the LLM Can't Find You, You Don't Exist: Discoverability for MCP-Apps and ChatGPT Apps - Vincent McLeese, Ghost Team

Thursday April 2, 2026 5:30pm - 5:55pm EDT

Broadway Ballroom South (6th Floor)

The next wave of MCP servers face the same challenge: discoverability. If an LLM doesn't know when to invoke your tool, it doesn't exist. This will compound - ChatGPT has ~80 apps today, but as more LLMs launch app stores and MCP adoption accelerates, there will be millions.

Drawing from research optimizing ChatGPT apps since launch, this talk reveals metadata patterns that determine whether AI systems surface your tools - principles that apply directly to MCP server development.

What I'll cover:
- Two-channel discovery: How static search (registries i.e. ChatGPT's App Store) and dynamic invocation (LLM tool selection) require different optimization strategies.

- How LLMs read metadata: How tool names, descriptions, and parameters shape invocation decisions.

- The golden prompt set: Testing methodology using direct, indirect, and negative prompts to measure recall and precision.

- What converts: Fixed templates, workflow handoffs, context preservation vs anti-patterns that fail.

- Measuring success: Citation tracking, false positive monitoring, and iteration loops that compound discoverability gains.

Speakers

Vincent McLeese

Product and Tech Lead, Ghost Team

Vincent McLeese is the Product and Tech Lead at Ghost Team, an
MCP Apps agency. He leads the development of appsdiscoverability.com,
a platform devloper by Ghost Team to help mcp apps become more
discoverable. A multiple founder with a background in tech strategy
from Accenture, Vinc

... Read More →

Thursday April 2, 2026 5:30pm - 5:55pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

11:30am EDT

Human in the Loop, Agent in the Flow - Harald Kirschner & Connor Peet, Microsoft

Friday April 3, 2026 11:30am - 11:55am EDT

Broadway Ballroom South (6th Floor)

The AI hype cycle promised full automation. Reality delivered hallucinations and agents that guess when they should ask. The MCP spec offers a different vision—humans in control through rich, interactive collaboration rather than micromanaging every step.

This talk explores how recent MCP primitives transform the protocol from text-in-text-out tool-calling into interactive human-agent workflows. We'll cover elicitations that let servers ask clarifying questions with structured forms, async tasks that pause for human decisions and resume seamlessly, and MCP Apps that render interactive UIs—charts, dashboards, confirmations—in sandboxed iframes. Each makes feedback loops faster and agent interactions richer.

Using VS Code's implementation as reference, we'll demonstrate patterns for adaptive autonomy, progressive input gathering, and bidirectional workflows where servers drive the conversation. You'll leave with concrete patterns for building MCP integrations that treat collaboration as a feature, not a fallback.

Speakers

Harald Kirschner

Principal PM, Microsoft

Harald Kirschner is a Principal Product Manager at Microsoft, building AI coding experiences in VS Code and GitHub Copilot for 40+ million developers. Before Microsoft, he led Firefox DevTools at Mozilla and helped ship Firefox Quantum. His engineering roots (MooTools, early web... Read More →

Connor Peet

Principal Software Engineer, Microsoft

Connor is a principal software engineer working on VS Code since 2019.

mcp vscode human in the loop url

Friday April 3, 2026 11:30am - 11:55am EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate
Session Slides Yes

12:00pm EDT

Distributing MCP Servers With OCI To Power Agent Skills - Bobby House, Docker

Friday April 3, 2026 12:00pm - 12:25pm EDT

Broadway Ballroom South (6th Floor)

While it is now considered a best practice for agent skills to leverage MCP servers, there is still no widely accepted approach for how those MCP servers should be distributed, versioned, and shared as dependencies.

This talk presents a practical pattern for using OCI artifacts as a distribution mechanism for MCP servers and configurations that agent skills depend on, enabling reproducible, shareable, and composable agent capabilities.

We’ll walk through creating an agent skill that can build and run an MCP project as a containerized service, then publish supporting artifacts such as the MCP server’s configuration.

Rather than bundling dependencies directly, the agent skill references an OCI artifact by OCI ref, pulls it at runtime, and activates the required MCP servers automatically. This ensures that when prompts expect specific MCP servers to be available, they already are.

By treating OCI as a universal distribution layer for agent tooling metadata and configurations, this approach makes agent skills easier to share, reproduce, and evolve across teams and environments.

Speakers

Bobby House

Sr Software Engineer, Docker

Bobby House is a senior software engineer at Docker that enjoys building products for engineers. His recent work centers on integrating MCP into enterprise environments by enabling organizations to publish and manage private catalogs of MCP servers as OCI artifacts.

agent skill dependencies pdf

Friday April 3, 2026 12:00pm - 12:25pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate
Session Slides Yes

12:30pm EDT

Solving Context Bloat: Semantic Tool Routing in Multi-Server MCP Environments - Hugo Guerrero, Kong

Friday April 3, 2026 12:30pm - 12:55pm EDT

Broadway Ballroom South (6th Floor)

Agentic systems adopting MCP face a scalability hurdle: managing interactions with numerous servers exposing dozens or hundreds of tools. Injecting all tools into the model context, or "context bloat," increases latency, inflates context window usage, drives up costs, and degrades reasoning quality.

This session introduces the MCP Gateway pattern, an architectural solution to context bloat. This pattern uses an MCP-aware routing layer to dynamically select and inject only the tools semantically relevant to a user request.

We will detail the design and implementation of semantic tool routing utilizing intent classification, embedding-based search, and lightweight prompt analysis. The talk will cover how this routing layer interacts with multiple MCP servers, maintains protocol correctness, and enables just-in-time tool discovery without overwhelming the model.

Attendees will receive a practical blueprint for building scalable, cost-efficient, and modular agentic systems based on MCP. The session emphasizes reusable patterns and reference architectures applicable across the broader MCP ecosystem, independent of any single vendor or runtime.

Speakers

Hugo Guerrero

Developer Advoate, Kong

Hugo Guerrero is a tech leader, speaker, and architect obsessed with AI, APIs, and the systems that connect them. From scaling developer ecosystems to mastering event-driven architecture, he focuses on making agentic connectivity a practical reality for modern enterprises. Passionate... Read More →

Beating Context Bloat MCP Dev Summit 2026 pdf

Friday April 3, 2026 12:30pm - 12:55pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Beginner

2:25pm EDT

The Tool Abstraction Problem: Lessons Learned Building 1000+ MCP Tools - Sam Partee, Arcade.dev

Friday April 3, 2026 2:25pm - 2:50pm EDT

Broadway Ballroom South (6th Floor)

Before MCP, Arcade was building tools for LLM agents. We've shipped over 1,000 tools—first as native Arcade tools with our own protocol and eventually adopting MCP. The main lesson: the hard part isn't writing the code, it's finding the right abstraction.

Most MCP tools today are thin wrappers around APIs. `GET /users/{id}` becomes `get_user(id)`. But this creates a mismatch—LLMs reason about tasks ("find the customer who complained last week"), not endpoints. The question is: where should tools sit on the abstraction spectrum?

**Too low-level:** The agent needs to chain together many calls. Each step is a chance to fail, and the model has to maintain context across all of them. You're asking the LLM to be a programmer at runtime.

**Too high-level:** You end up enumerating every possible task as its own tool. This defeats the point of having a general-purpose agent and your tool schema balloons, eating context and degrading selection accuracy.

In this talk:

- The common pitfalls we see in MCP tool design
- Our design philosophy for optimized tools
- Multiple real-world use cases and the tools that work for them
- Outlook on future tool development

Speakers

Sam Partee

CTO and Co-founder, Arcade.dev

Sam is the CTO and co-founder of Arcade.dev. Before starting Arcade, Sam lead the led the applied AI team at Redis responsible for the vector database offering. He is a avid OSS developer and has contributed on projects like Langchain, LlamaIndex, Chapel, DeterminedAI, and others... Read More →

MCP Dev Summit pptx

Friday April 3, 2026 2:25pm - 2:50pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Advanced
Session Slides Yes

2:55pm EDT

The MCP Gateway Pattern: Aggregation, Composition, and Beyond - Juan Antonio Osorio, Stacklok

Friday April 3, 2026 2:55pm - 3:20pm EDT

Broadway Ballroom South (6th Floor)

Here's a scenario that might sound familiar: you've got ten MCP servers, which means ten client connections, ten auth flows, and ten different places where things can break. One reason teams end up in this mess is that each MCP server solves a real problem - so you add another one, and another, and suddenly you've got MCP sprawl.

Enter the MCP Gateway pattern.

In this talk, we'll walk through an architecture that aggregates multiple MCP backends behind a single unified interface. We'll cover the fun problems this creates - what happens when two backends expose tools with the same name? and show how declarative workflow composition lets you orchestrate multi-step operations across backends without writing custom wrapper code.

We'll demo a gateway unifying several backends and executing a workflow defined entirely in YAML. No magic, just patterns you can apply to your own infrastructure.

With this in mind, you'll leave with practical approaches to taming MCP sprawl while keeping your security policies consistent across the board.

Speakers

Juan A. Osorio

Principal Engineer, Stacklok

Juan Antonio "Ozz" Osorio is a Mexican software engineer living in Finland. His background spans security for OpenStack, Kubernetes, and bare metal environments. Currently at Stacklok, he founded the ToolHive project and has been building MCP infrastructure, including supply chain... Read More →

Presentation 10 MCP Servers pdf

Friday April 3, 2026 2:55pm - 3:20pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Advanced
Session Slides Yes

3:25pm EDT

From Benchmarks To Business Value: Building a Use-Case Specific Agent Evaluation Framework - Gaurav Saxena, Independent & Matvey Kukuy, Archestra.AI

Friday April 3, 2026 3:25pm - 3:50pm EDT

Broadway Ballroom South (6th Floor)

While frontier models achieve impressive scores on benchmarks like MCP Atlas (62.3%) and SWE-bench (62.1%), these metrics don't answer the critical question: "Will this agent work for OUR specific use-case?"This talk presents a practical framework for building custom agent evaluation systems tailored to your organization's needs. We'll cover the complete lifecycle: data collection and categorization, open-source instrumentation patterns, and production monitoring for long-term performance tracking. You'll learn to construct evaluation datasets reflecting actual workloads, implement testing harnesses mirroring production constraints, and establish monitoring pipelines that catch degradations early.We'll demonstrate techniques for measuring agent reliability across accuracy, latency, cost, and safety dimensions while accounting for real-world variables: prompt engineering, data quality, MCP tool availability, and model selection. Attendees will leave with actionable strategies to build confidence in production deployments and create feedback loops for continuous improvement.

Speakers

Gaurav Saxena

Director of Engineering

Gaurav Saxena is an engineering leader in the field of platform and cloud engineering with over 20 years of experience in the software industry. His technical expertise includes Stream-based architectures, Kubernetes, Service Mesh, Software Supply Chain Security, and Observabilit... Read More →

Matvey Kukuy

CEO, Archestra.AI

Maintainer: Grafana OnCall, KeepHQ, Archestra.AI.

Ex-Engineering Director at Grafana Labs.

Friday April 3, 2026 3:25pm - 3:50pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

4:20pm EDT

MCP Servers in the Wild: Managing Tool Complexity at Scale - Arnav Balyan, Concierge AI

Friday April 3, 2026 4:20pm - 4:45pm EDT

Broadway Ballroom South (6th Floor)

As MCPs are adopted at scale, certain patterns start to emerge:
1. Increase in wrong tool calls
2. increase in token usage, semantic loss
3. agents skipping the required tool call sequence.

For high stakes domains such as finance and infrastructure, this leads to reliability and compliance risk.

This talk presents a new MCP server design pattern for addressing this class of problems called: "progressive tool exposure".
Rather than assuming static tools, the MCP server actively controls which tools are visible to the agent at each point in execution. This framework ensures, tools are refreshed, scoped, and changed as the agent progresses through an MCP workflow. This allows the server to direct the agent’s action space, guide execution order, and enforce "runbooks" without changing server/ agent capability. This design pattern also tracks state ensuring backtracking of tool calls reverts the server side state, making agent behaviour as transactional on the MCP server.

We show how such practices reduce invalid tool calls, lower inference costs, and improve determinism for tool heavy systems.

Speakers

Arnav Balyan

CEO, Concierge AI

Founder of Concierge AI. Ex-Uber building MCP systems at scale. Concierge AI manages 400+ public MCP deployments, Arnav focuses on MCP tool complexity and researches token overhead reduction at scale.

Friday April 3, 2026 4:20pm - 4:45pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate

4:50pm EDT

Your MCP Server Will Probably Be Abandoned...Or Not - Lahari Chowtoori, Amazon Web Services, Inc.

Friday April 3, 2026 4:50pm - 5:15pm EDT

Broadway Ballroom South (6th Floor)

Here's what's going to happen: MCP takes off. Hundreds of MCP servers get built. Most of them end up unmaintained within two years and then issues pile up, PRs go stale, the original author moves on.

I have spent time digging through MCPZoo, a dataset of 56,000+ MCP servers, and the warning signs are already there. Repos with READMEs that just say "install and run." Projects with one contributor and no activity in months. Issues sitting unanswered. The ecosystem is growing fast, but a lot of what's being built has "abandoned in 6 months" written all over it.

I'm sure some of you have tried contributing to these projects. Couldn't run the tests. Couldn't understand the structure. Couldn't tell if anyone was still around. That friction isn't just annoying, it's why maintainers burn out and contributors disappear.

In this talk, I'll break down what makes an MCP server thrive or die. Projects die when newcomers can't onboard, can't run tests, can't understand the structure. The ones that survive do specific things: working CI from day one, a README that gets someone running in under 5 minutes, clear contributor guidelines. I'll show you how to set up your own projects to last.

Speakers

Lahari Chowtoori

Open Source TPM, AI/ML, AWS

Lahari Chowtoori is an AI enthusiast and Technical Program Manager at AWS, focusing on open source, Machine Learning, and Artificial Intelligence. With a background in Data Science and Machine Learning, she is passionate about democratizing AI knowledge and fostering community collaboration.She... Read More →

Friday April 3, 2026 4:50pm - 5:15pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Any

5:20pm EDT

Reflections on Context Engineering Via MCP Servers - Till Döhmen, MotherDuck

Friday April 3, 2026 5:20pm - 5:45pm EDT

Broadway Ballroom South (6th Floor)

Effective context engineering via MCP servers requires understanding how host agents weave the server's responses into their context as conversations unfold.

Context flows through more channels than tool definitions alone: initial instructions, the tool set itself (explicit tools vs. generic execution tools), tool names and parameters, descriptions, response content, structure and length, error feedback, "skill-loading" tools, resources, and sub-agent delegation.

Each mechanism involves trade-offs. Eager loading of context risks bloat; lazy loading adds tool calls. Rich tool responses help agents self-correct but consume tokens. Sub-agents compartmentalize complexity, but limited client support for elicitation creates friction.

Getting this balance right means staying conscious of how much context you're injecting, when, and at what cost (e.g. in # of tool calls to achieve a goal)—a balancing act that's hard without a clear picture of what's happening inside the host agent's context window.

This talk aims at providing a framework for thinking about these decisions—grounded in concrete examples from building the MotherDuck MCP Server.

Speakers

Till Döhmen

AI Lead, MotherDuck

Till Döhmen is AI Lead at MotherDuck, where he focuses on building agentic experiences for data analytics. He designed and built the MotherDuck MCP Server, enabling AI agents to query and analyze data through Claude, Cursor, and other MCP clients. Till is also a final-year PhD candidate... Read More →

Friday April 3, 2026 5:20pm - 5:45pm EDT
Broadway Ballroom South (6th Floor)

MCP Best Practices

Audience Experience Level Intermediate
Session Slides Yes

11:50am EDT

12:20pm EDT

12:50pm EDT

2:35pm EDT

3:05pm EDT

3:35pm EDT

4:30pm EDT

5:00pm EDT

5:30pm EDT

11:30am EDT

12:00pm EDT

12:30pm EDT

2:25pm EDT

2:55pm EDT

3:25pm EDT

4:20pm EDT

4:50pm EDT

5:20pm EDT

Get help with the event