cd /news/ai-agents/i-built-a-jungle-survival-browser-ga… · home topics ai-agents article
[ARTICLE · art-121206] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

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.

read2 min views1 publishedSep 4, 2026

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 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, 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/positionget_planning_context

— dusk only, returns expected enemies and defense optionsplace_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.

── more in #ai-agents 4 stories · sorted by recency
── more on @webmcp 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-a-jungle-sur…] indexed:0 read:2min 2026-09-04 ·