From Request-Response to Collaboration

When I wrote about the CLI vs MCP debate [1], I focused on the infrastructure patterns underneath. But MCP itself has been evolving, and the latest additions change what’s architecturally possible.

The Model Context Protocol started as a clean way for AI agents to call tools: agent sends request, server returns response. Simple, stateless, effective. But real-world agent workflows need more than request-response. They need the server to ask questions back.

The Fifteen-Year Echo

In 2010, Adrian Cockcroft stood on the QCon stage and told the audience that Netflix was running its entire business on a public cloud. Most people in the room thought he was crazy.

Fifteen years later, Cockcroft was back at QCon, this time explaining how he manages swarms of autonomous AI agents that produce several days’ worth of code in fifteen minutes [1]. The audience reaction was different. Nobody called him crazy. They were taking notes.

Namaste from 6,165 Meters

I just summited Imja Tse (Island Peak, 6,165 meters) in Nepal. No Slack, no email, no MCP servers crashing in the background. Just ice, thin air, and the kind of clarity that only comes when every step costs you something.

At that altitude, you don’t tolerate inefficiency. Every piece of gear earns its place or stays behind. Every movement is deliberate. You can’t afford to fumble with equipment that doesn’t work the first time.

The Zombie Processes and the 50GB Cache

A few weeks ago, I noticed my MacBook was sluggish. I found orphaned MCP server processes that had failed to shut down cleanly — a problem Didier Durand describes vividly in his analysis [2], where users report finding over 100 zombie Node.js processes after a single session. I killed mine, freed some RAM, and went back to work.

Then last week, Brooke Jamieson — a fellow AWS Developer Advocate — published a post about running uv cache prune and freeing 75GB of disk space [9]. The culprit? Every uvx invocation from MCP servers (Kiro, Cursor, Claude Code all use them under the hood) silently caches packages, and the cache never cleans itself up. I ran the same command and got back 50GB. Fifty gigabytes of invisible MCP debt, sitting on my drive.

🎯 From Chaos to Control: Building Predictable AI Agents That Get Smarter Over Time

⚖️ We need to balance Agency versus Control. We want AI systems to be super easy to use, read our minds, and just provide the answer we need. But we also need to make sure that nothing goes wrong. The more we control, the less agency we get. This is a balancing act.

Let’s focus on the control part. There are many different mechanisms to increase and guarantee control. Things like policies and guardrails come to mind. Those are obvious and powerful. I will cover them in a dedicated post.

Kind of an interesting twist in IT history: Did it need the advent of AI Agents to drive developer friendly, standardized and discoverable interfaces to systems?

Recently Model Context Protocol (MCP) got a lot of attention and traction. While this is good and exciting thing, I was wondering why this is actual needed? In a perfect & developer friendly world, it shouldn’t need another protocol just for agents, does it? AI should easily be able to use the existing interfaces, which have been built for convenience of human developers, no?