MCP Dev Summit Mumbai 2026

18 months ago, Block open-sourced an agent framework called Goose. Community grew quickly,  faster than I ever expected. Then the community came back with a question I didn't have a good answer to: who keeps this open?
This is the story of chasing that answer - how it led to a foundation co-founded by fierce rivals, why nearly two hundred companies have since joined, and what we've learned about open along the way. Because open, on its own, doesn't stay open; we've seen that movie before, and the agentic layer raises the stakes higher than anything that came before it.
It's also a look forward - to the future we're building toward, where agents from any vendor can find each other, trust each other, and transact on rails no single company, or government, can ever pull out from under us. The agentic layer is still being shaped. This talk is about how we keep it open, and how you can help, while it's still ours to shape.

Goose is an open-source AI agent that can be extended through integrations, tools, and community-driven projects. In this talk, I'll share my journey working with Goose, explore how its capabilities can be extended through community-driven projects, highlight examples from the Goose ecosystem, and discuss the development of GooseBot as one approach to bringing AI agents closer to developer communities. Along the way, I'll cover lessons learned from building in the open and why extensibility is key to the future of open-source AI agents.

MCP is the protocol layer for the new consumer of software. But protocols are necessary, not sufficient. The next generation of agents won't be soley defined by the protocol they speak — but also the infrastructure that powers it.

In this keynote, Sam Partee (CTO and Co-Founder of Arcade.dev) walks through the agent runtime components needed to drive more adoption of MCP: delegated identity that scopes what an agent can do; tool routing that survives ten thousand registered tools; memory and provenance that turns one-shot demos into auditable systems. Each layer is grounded in production data — what breaks, mistakes we made, what to build, why, and what the next two years of infrastructure work look like.

MCP reached infrastructure currency in 13 weeks. CNCF took 13 months. That compression is the problem. The shared plumbing every production MCP deployment now reinvents, because no neutral open implementation exists yet, has to be built in months instead of years.

This talk maps five missing layers of the MCP ecosystem and what each needs before the protocol scales two more orders of magnitude.

1. Discovery federation. One registry lookup does not survive public, private, and vendor registries coexisting.
2. Workload identity for servers. Not user OAuth. Who is this server, who signed it, what is it allowed to do?
3. Observability backbone. OpenTelemetry semantic conventions for MCP are still draft, so every gateway ships its own trace format.
4. Health and reputation signals. When seventeen servers are named github-mcp, which one should an agent trust?
5. Metering and cost attribution. Boring, load bearing, absent from the spec.

For each layer: what exists today, where it breaks at scale, what a minimum viable open implementation needs. Attendees leave with a concrete map of which gaps are urgent, which are deferrable, and which are already being filled.

The Model Context Protocol (MCP) has fundamentally revolutionized developer velocity, allowing engineers to build and iterate complex AI agents seamlessly on a local machine. However, when moving these autonomous agents from a local sandbox into a production enterprise environment, organizations hit a sudden architectural ceiling. The local agility that fuels early-stage innovation quickly breaks under the compounding pressure of agentic sprawl, fragmented data integrations, and critical compliance requirements.

This keynote addresses the hidden architectural dimensions required to run enterprise AI agents safely and reliably at scale. Moving past individual agent scripts, we will explore why a centralized, fully managed platform is no longer a luxury, but a core system dependency. We will dive into the four essential pillars—Build, Scale, Govern, and Optimize—with a specific focus on how a managed MCP control plane provides the cryptographically-attested identity, granular gateway policies, and runtime isolation required to cross the chasm from an impressive local prototype to a secure, enterprise-grade AI ecosystem.