OpenNashPodcasts

Topic

Craig McLuckie

10 facts from 1 episode, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.

Undated

Craig McLuckie says he and a colleague named Joe built Google Compute Engine, Google's virtual machine infrastructure service.

“I was, uh, happy to meet my friend Joe and we built out, uh, Google Compute Engine, which is, you know, virtual machine infrastructure technology.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:01:52

Undated

McLuckie says he and his colleague started the Kubernetes project while at Google and later built other technologies together.

“We started the Kubernetes project, did a few other things, you know, inside there, we, you know, subsequently, we've built a lot of other, uh, technologies together.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:02:15

Undated

McLuckie says an MCP platform has four pieces: a runtime, a registry, a gateway and a control plane.

“I think of as being four pieces that go into that. The 1st piece that goes into that is I need a runtime, I need somewhere where I can run this thing”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:15:28

Undated

McLuckie says developers commonly run MCP servers by pulling a package from the internet with npx and running it locally, which risks running exploited code.

“In the case of, you know, most development technologies, people go npx run. They basically just pull a package down from the internet and it runs locally.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:15:28

Undated

McLuckie says his CTO Joe wrote the SPIFFE paper, about a zero-trust identity framework, around ten years earlier.

“He wrote the Spiffy paper, I don't know if you've heard of Spiffy. It's it's an identity system that's kind of, uh, a sort of, the sort of zero trust”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:21:51

Undated

McLuckie describes agent identity as a three-legged stool: a service account identity for the agent, claims from the agent owner's role, and on-behalf-of claims inherited from the user.

“There's what I think of as a service account identity that's effectively identifying the agentic endpoint.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:23:20

Undated

McLuckie says replacing many tool listings with find-tool and invoke-tool endpoints reduces input token consumption by 80 to 90%.

“It reduces input token consumption by eighty to 90% when you have these these things, and so that's a very big deal.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:30:15

Undated

McLuckie says a single guided endpoint can raise tool-calling reliability by smaller models back to roughly 95-97%.

“You can get back up to the sort of ninety five, ninety seven threshold that actually makes the system useful.”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:31:09

Undated

McLuckie predicts AI systems will generate Kubernetes YAML manifests from descriptions and monitor deployments, stepping in when ordinary reconciliation fails.

“you'll be able to, you know, describe what you want to have happen, you know. It'll basically generate the YAML manifest, hand it off to Kubernetes”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:41:35

Undated

McLuckie says Stacklok developers run between five and 15 concurrent agents, each configured with a different role and controlled tool access.

“they'll have 15 different agents, each with a slightly different configuration recipe role, uh, performing a set of tasks”

Craig McLuckie · Rebooting Enterprise AI with MCP and Kubernetes, 0:45:26

Episodes