mcpField
A
Antics

Antics

Local
github.com/antics-ggAI & Agents5Updated 14w ago

About Antics

Antics is an MCP server for AI agents that deploys web games to playable multiplayer URLs. It handles rooms, live state synchronization, and leaderboards, with keyless ephemeral deployment available without login.

Key features

  1. 01Deploy single-file or multi-file web games
  2. 02Generate shareable multiplayer URLs
  3. 03Support rooms and live state synchronization
  4. 04Create projects and access leaderboards
  5. 05Set social link preview details

Use cases

  1. 01Publish an AI-generated game for friends to play
  2. 02Create a multiplayer game in one conversation
  3. 03Read scores from a project leaderboard

MCP support

Antics exposes game deployment, project, leaderboard, and share-preview tools to MCP clients. The keyless deploy_game tool can return an ephemeral playable URL without login.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"antics": {
"command": "npx",
"args": [
"-y",
"antics-mcp"
]
}
}
}
Run commandnpx -y antics-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmantics-mcp0.5.1

Tools

14

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
topicenumNoOmit for the classic-tier SDK reference; 'sim' for the sim-tier (sim.js) authoring contract.sim

Details

From the project README

antics-mcp

Multiplayer for your game, in one prompt. An MCP server that lets an AI agent generate a web game and deploy it to a playable multiplayer URL — rooms, live state sync, and leaderboards — inside a single conversation.

AI can write a whole game — a single HTML file or a multi-file project — but it can't stand up a server, so everything it builds is single-player. antics-mcp is the missing piece: your agent writes the game, calls one tool, and hands you back a link your friends can open. No backend, no player accounts.

→ antics.gg · full API in one file: antics.gg/llms.txt

Install

Claude Code:

claude mcp add antics -- npx -y antics-mcp

Claude Desktop / Cursor / any MCP client — add to your MCP config (claude_desktop_config.json, Cursor's mcp.json, etc.):

{
  "mcpServers": {
    "antics": {
      "command": "npx",
      "args": ["-y", "antics-mcp"]
    }
  }
}

Then just ask: “Make a 2-player game and deploy it.” The agent writes it, calls deploy_game, and returns a playable URL — no copy-paste, no site visit, no login.

Tools

ToolWhat it doesLogin?
deploy_gameDeploy a game (html for a single file, or files for a multi-file project) → returns a playable multiplayer URL. Keyless (ephemeral room) unless given a projectId.No
create_projectCreate a project; returns its id, publishable key (pk_), and secret key (sk_, shown once).Yes
get_leaderboardRead a project's leaderboard (top scores).Yes
list_projectsList your projects.Yes
set_share_previewBrand how a project's room links unfurl on social — title, description, and image.Yes

deploy_game works without any login — it returns an ephemeral, keyless URL you can share immediately (rooms hold 8 players and last 24h). To persist links + leaderboards and raise the limits, sign in once with npx antics-cli login (GitHub), then the owner-scoped tools unlock and deploy_game can target a project.

How the multiplayer works

Your agent doesn't need to know any of this up front — antics.gg/llms.txt is the complete API in one file, written so an LLM can integrate it one-shot. In brief: a game calls joinRoom({}), shared room state is host-authoritative with per-player slices, writes coalesce to ~20 Hz, and a leaderboard is one submitScore() call. The deployed game runs at a /r/<code> URL with an invite link + QR built in.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.