MCPet MCP Server

This is a TypeScript-based Model Context Protocol (MCP) server that implements a virtual pet simulation system. It demonstrates core MCP concepts by providing tools for pet care and interaction. The mcpet mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

MCPet: A nostalgic virtual pet experience for the AI age! This Model Context Protocol (MCP) server lets you adopt, nurture, and play with your very own digital companion that evolves based on your care. Feed them, clean them, play games together, and watch them grow from a baby to an adult. Your pet's stats change over time even when you're away - just like the classic Tamagotchi toys, but powered by modern AI through the Model Context Protocol. Adopt your digital friend today!

Its toolset

Everything the assistant can do here goes through one of these:

• create_pet — Adopt a new pet with a custom name and type
• check_pet — View your pet's current status and stats
• feed_pet — Feed your pet with different food options:
• Snack — Small hunger boost
• Meal — Balanced nutrition
• Feast — Maximum feeding (but can be unhealthy)
• play_with_pet — Play different games:
• Ball — Light exercise
• Chase — High energy fun
• Puzzle — Mental stimulation
• clean_pet — Give your pet a bath to restore cleanliness
• put_to_bed — Let your pet sleep to restore energy

Configuration

You will need one environment variable: PET_DATA_DIR. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCPet's toolset — create_pet, check_pet, feed_pet and 11 more — is a fair guide to whether it matches your workflow. It is maintained by shreyaskarnik; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCPet's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCPet.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the mcpet mcp server does with a few real requests.