What goes into a solid MCP registry?

Bill Doerrfeld | March 31, 2026

My latest for InfoWorld explores what an MCP registry is and what makes an enterprise-grade MCP registry production-ready for AI agents.

How do you govern hundreds of MCP servers in an enterprise? MCP registries are emerging as a way to unify and manage a catalog of approved tools, helping with discovery, governance, and safe usage in agentic systems.


But there is a right way to do it at scale. As Christian Posta says, if you're treating an MCP registry as "just another static catalog," you're doing it wrong.


A quality MCP registry requires rich, semantic tool metadata, developer-friendly controls, clear privilege boundaries, and thoughtful decisions around public versus private registries.


In short, MCP registries are becoming a core control plane for governing how AI agents discover and use tools across enterprise systems.


I got a ton of interest from sources on this one, which says a lot about the development energy around MCP and agentic infrastructure right now.

Read: How to build an enterprise-grade MCP registry

Other Blog Posts

KubeCon + CloudNativeCon North America 2026 keynote stage with the

The new Kubernetes production workload: AI inference

By Bill Doerrfeld • November 10, 2026
At KubeCon NA 2026, the opening keynotes made it clear: AI inference is the new cloud native production workload. Here's what that means for Kubernetes.
Agentics Day: MCP + Agents North America title slide on the screen at KubeCon NA 2026

8 takeaways from Agentics Day: MCP + Agents

By Bill Doerrfeld • November 10, 2026
Agents are getting production tested. I explore some of the top lessons learned at KubeCon NA 2026's co-located event, Agentics Day: MCP + Agents.
KubeCon + CloudNativeCon North America 2026 graphic: November 9-12, Salt Lake City, Utah

See you at KubeCon NA 2026!

By Bill Doerrfeld • November 6, 2026
I'll be at KubeCon + CloudNativeCon NA 2026 in Salt Lake City, Nov 9–12, scouting stories on agentic AI, cloud native and APIs. Reach out if you'd like to connect!
AI Pen-Testing Conference graphic from AI Security University

AI pen-testing virtual conference is a wrap!

By Bill Doerrfeld • November 4, 2026
Another virtual conference is in the bag, and the community really showed up to talk AI penetration testing.

My Road to KubeCon series is a wrap!

By Bill Doerrfeld • October 30, 2026
My eight-part Road to KubeCon column with The New Stack is done. Here are some of the key takeaways.
How AI Agents Change API Interaction opening slide doerrfeld bill 2026 nordic apis

My slides for my keynote 'How AI Agents Change API Interaction'

By Bill Doerrfeld • October 18, 2026
Here are my slides from my opening keynote at Nordic APIs Summit 2026, exploring how AI agents are changing API interaction patterns.

The AI Pen-Testing Toolbox

By Bill Doerrfeld • October 17, 2026
My latest research for AI Security University looks at AI tools and resources for pen-testers, red teamers, and bug bounty hunters.

Agents redefine the software delivery lifecycle

By Bill Doerrfeld • October 16, 2026
My commissioned feature for Arthur D. Little's PRISM publication analyzes the big shifts underway now that generating code is becoming trivial.

Thanks for having me, SecureMaine!

By Bill Doerrfeld • October 11, 2026
Was happy to participate as a speaker and moderator at SecureMaine on October 8th, 2026.

How Meta is scaling senior engineering knowledge

By Bill Doerrfeld • October 5, 2026
My latest for LeadDev interviews a Meta engineer who built an agentic system to optimize their capacity planning, leading to real power use savings.