How creating an MCP server for my game showed me clearly the limits of current AI (Opus 4.7) - Carrot & Stick

2026-04-30 20:57

How creating an MCP server for my game showed me clearly the limits of current AI (Opus 4.7)

Intro note: I kinda struggled writing this blog post. So I asked Claude to interview me. And honestly his questions are super relevant, so we're not changing anything in what he asked — I'll just try to answer.

Q1 — Just to start somewhere: introduce yourself quickly, and tell me what Carrot & Stick is. Not a pitch — just what it is, how it came about, where you are today.

My name is Octave Soundberg. I created Carrot & Stick about a year ago, when my son asked me: "dad, you told me you'd help me create my video game, so please can you help me?" And I started building this game with him.

At first it wasn't called Carrot & Stick, it was called something else. But one day, when the game started to get serious, my son told me: "dad, that's my intellectual property, that's my universe, so I want you to rename it." So I'm not gonna tell you the name my son had for his game, it's another universe. That's what led me to create Carrot & Stick: a little carrot with a stick that's gonna try to save the world from pollution.

I started developing it in January 2025, and I started going full-time on it in June 2025, when a friend who's done a lot of startups and raised a lot of money told me: "but actually what you have is great, so go all-in." That's what motivated me.

Q2 — Now let's jump into it. At some point, you decided to build an MCP server for Carrot & Stick that lets any Claude.ai user create levels in your game by talking to the AI. When was that? And more importantly: what did you expect by doing that? Did you think it would be magic? Did you think LLMs would make levels better than you? Were you just testing to see? Tell me your state of mind at the time.

When I created the first MCP server for Carrot & Stick, I told myself: this is gonna be great because it'll let people create their own levels directly through MCP. At the time, MCPs were something very new, basically nobody had made one.

I ran into a lot of problems: I had to create an OAuth server, dig through documentation that was pretty erratic and incomplete in the beginning. Several times I gave up, because I think the language models weren't strong enough yet to implement it, and I didn't have the skills yet either.

Then at some point I managed to get it working a first time, but it required creating an account, there was a whole bunch of complicated stuff. I finally recently managed to do it completely: you just go into Claude (the desktop app), into the MCP add menu, enter the URL, validate, it redirects to the web window, you log in, you're redirected back to Claude and right away you can start interacting with the Carrot & Stick MCP server and create levels with Claude's help.

I told myself: this is gonna be great, it'll let people create levels from Claude and from other LLMs. I already have a level editor in Carrot & Stick that lets people create their own level, but here I told myself we can go much further by letting people create levels in just a few sentences dictated to an LLM. It opens up a ton of possibilities.

I thought LLMs could make levels way better than humans — why not — or at least roughly at the level of humans. That was kinda the basic idea. And I'd also told myself that MCP servers are a goldmine, it's great, few people are making them, and maybe it can bring me curious users who'd want to try level creation through LLM.

Knowing that my game, I created it for my son and for my other son. It's had a pretty big success with young kids, and especially intergenerationally: it lets adults create levels, kids play the levels, kids create levels, adults play. Basically it's a creation and play tool between multiple generations. That's kinda how I designed it too.

Q3 — OK so you've finally launched it, it's in prod, anyone can connect their Claude to C&S and say "Claude, make me a level". You start the first tests. You start asking Claude to generate levels and you play them. Does it match your expectations? Or is there a moment where you go "ah shit"? Tell me about the first real test, what you asked, what came out, and how you felt at that moment.

There were a lot of tests, and very quickly I told myself: in the end the levels look pretty similar. I tried to feed information to Claude so he could transform it into blocks he could position. But very quickly I realized the levels created by AI looked really pretty similar.

So I started thinking: ok, what can we do to improve this? I thought about it, asked myself a lot of questions, and started thinking: maybe I could feed the levels I've already created as raw material to train the model.

And there, very quickly, I realized I needed to compress the information. Because when you have a lot of blocks, the signal in the end is squares with lots of...