I built a jungle survival browser game where you co-op with an AI agent

A developer built Erwin's Survival, a browser game where a human co-opts with an AI agent to survive in a jungle. The game uses WebMCP to let the AI place defenses during a planning phase, while the human handles real-time actions. The developer scrapped an initial version where the AI did everything, finding that splitting roles improved the experience.

This is my first post here. I figured I should start somewhere, and a hackathon project is as good a reason as any. I have been writing business software for about three years. Dashboards, APIs, data pipelines. It pays the bills but it stopped being fun a while ago. When I saw the WebMCP Challenge https://webmcp.devpost.com/ hackathon, I decided to build something I would actually want to play when it was done. This is also my first game. Never touched game loops, sprite rendering, or canvas animation before this week. Erwin's Survival is a browser game where a human and an AI agent play together. The human explores a jungle, collects resources, and builds a base. The AI reads the game state through WebMCP tools and places defenses before each night attack. The game has three simple phases that repeat for three days: Survive 3 nights and rescue arrives. The game uses WebMCP https://developer.chrome.com/docs/extensions/develop/concepts/webmcp , which lets a website expose tools that an external AI agent can discover and call. The game registers 5 tools. Four of them only exist during the dusk phase: get game state — always available, returns health/inventory/position get planning context — dusk only, returns expected enemies and defense options place spike trap {side} — costs 2 wood + 1 stone build barricade {side} — costs 3 wood set fire {side} — costs 1 wood + 1 herbsWhen night falls, the defense tools are unregistered. The AI's job is done until the next dusk. I tested it with Chrome's WebMCP flag and the Model Context Tool Inspector extension by François Beaufort. You type something like "plan the defense" and the AI calls the tools one by one. Each call updates the game map in real time. The first version had the AI doing everything: gather water, eat berries, chop wood, craft items. All through WebMCP tools. It worked, but it was boring. Typing "gather water" to an AI when pressing R does the same thing is just friction. On day 2, I scrapped that and gave the AI only the planning phase. That was the right call. The keyboard handles actions. The AI handles strategy. Both halves got better once I stopped forcing everything through one channel. If you want to test the WebMCP tools, you need Chrome 146+ with the chrome://flags/ enable-webmcp-testing flag enabled, plus the Model Context Tool Inspector extension. Or just add ?debug=true to the URL for manual buttons. Three days, one game, a lot of sprite cropping. It was fun. Might do more of these.