MCP Dev Summit Bengaluru 2026

For fifty years, software has been built around one consumer: the human user. Every API pattern, every UX principle, every interaction model has assumed a person on the other end. In the last eighteen months, that assumption broke.

The consumer of software is increasingly not a person — it's a language model, reasoning about systems on our behalf. The Model Context Protocol is the first widely adopted standard for this new world, but MCP is just the skeleton. The real work — designing for the machine experience — is a discipline we are inventing in real time.

In this opening keynote, Sam Partee (CTO and Co-Founder of Arcade.dev) frames where we are, what's at stake, and why the builders in this room have a once-in-a-generation opportunity to define how software will be designed, secured, and consumed for the next decade.

What does it take to build agentic AI systems that are scalable, affordable, and trustworthy for India? This keynote explores the emerging AI stack powering next-generation healthcare and public service workflows from frontier and small models to interoperable MCP architectures and DPI integration.

Speakers from the Gates Foundation, Eka Care, and EkStep Foundation discuss the technical and governance choices that will shape AI deployment across India and other emerging markets.

MCP demos are easy. Production MCP is not.

Once a remote MCP server touches real data or privileged actions, a successful tool call is not enough. Teams need OAuth 2.1 done correctly, least-privilege scopes, protected resource metadata, audience-bound tokens, secure session handling, gateway-aware controls, and audit trails that explain who requested what and what the server actually did.

This session turns MCP’s security guidance into a practical production blueprint. I’ll walk through how to secure remote MCP servers end to end: when authorization is required, how to avoid token passthrough and over-broad scopes, where session isolation fails, what proxies and gateways must enforce, and what to log for debugging, compliance, and incident response.

Attendees will leave with a clear mental model, a reference architecture, and a concrete checklist for operating MCP clients, servers, and intermediaries safely in production.

This is just not about a single organisation but for every organisation, tool schemas in MCP evolve as platforms change parameters get renamed, new required fields are added, response shapes shift. Agents built against an older schema break silently, produce incorrect results, or enter undefined behavior, and there is no established SemVer discipline for MCP tools today. This session proposes a practical versioning specification for MCP tool definitions covering additive-only change policies, explicit deprecation signals embedded in tool metadata, capability negotiation via request headers, and client-side schema compatibility layers. The session demonstrates these patterns with a real Kubernetes tool server that ships v1 and v2 tool definitions side by side, with running agents targeting each version independently, and a live migration showing how a breaking change is introduced and absorbed without downtime.