tamagotchi-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tamagotchi-mcpcheck my pet's status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tamagotchi MCP
MCP server (stdio) that lets an LLM care for a virtual pet. Read-only web UI shows the pet's state in real time.
Setup
npm install
npm run buildRelated MCP server: Chess MCP Server
Usage
MCP server -- add to your MCP client config:
{
"mcpServers": {
"tamagotchi": {
"command": "node",
"args": ["/path/to/tamagotchi-mcp-2/dist/index.js"]
}
}
}Web UI -- run in a separate terminal:
node dist/server.js
# → http://localhost:3333Tools
Tool | Params | Effect |
| -- | Full state: stats, mood, age, recent actions |
|
| Restores hunger/happiness/health |
|
| Boosts happiness, costs energy |
| -- | +40 energy (requires energy < 60) |
| -- | +30 health (requires health < 70) |
|
| Changes pet name |
|
| Transforms pet, resets stats to 70 |
| -- | Revives dead pet, all stats to 50 |
Stat Decay
Hunger: -1 every 2 min
Happiness: -1 every 3 min
Energy: -1 every 4 min
Health: -1 every 5 min (only when hunger < 20)
Pet dies if hunger or health reaches 0.
Architecture
src/index.ts → MCP server (stdio), tool definitions
src/pet.ts → Game logic, types, decay, persistence
src/server.ts → HTTP server for web UI
data/pet.json → Persistent pet state
web/index.html → Pixel art UI (canvas sprites, CSS animations, polling)The web UI is read-only. All control happens through the LLM via MCP tools.
This server cannot be deployed
Maintenance
Related MCP Connectors
LLM Observability & Orchestration Agent (LangChain Community)
Minimal chat-first app with durable threads, actions, and the app-agent loop
LLM Observability & Orchestration Agent (Langchain)
LLM Observability & Orchestration Agent
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment10149 npm299MIT
- AlicenseAqualityAmaintenanceEnables Large Language Models to play chess agentically with real-time HTML board visualization and a hybrid AI engine featuring ten difficulty levels. It supports interactive games between users and agents, including a web dashboard to monitor active matches.4MIT
- AlicenseAqualityDmaintenanceGive your AI agent a persistent pixel-art character that reflects its state in real time.42MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with web applications through DOM inspection, user interaction simulation, and application state management.MIT