mcpField
M
MCP CONNECT 4

MCP CONNECT 4

Local
github.com/toliosGames & Entertainment1Updated 82w ago

About MCP CONNECT 4

MCP CONNECT 4 is an MCP server for playing Connect 4 with an assistant. It keeps the game state structured, with the assistant making both its own move and the player's move.

Key features

  1. 01Maintain structured game state
  2. 02Play Connect 4 through an assistant
  3. 03Have the assistant make both moves

Use cases

  1. 01Play a Connect 4 game in an assistant chat
  2. 02Use a game as an assistant interaction

MCP support

It exposes Connect 4 gameplay and structured game state to MCP clients.

Configuration

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

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP CONNECT 4

While people use MCP to build powerful connections with various tools like db's or the web one can imagine a great and perhaps more advanced interaction between user and assistant, would be to play a game. So I say why not. Let's play games!

This is the premise behind this repo. Also its fun!

MCP Connect 4 offers structure to the state of the game. The assistant plays the move it believes and also plays your move. (this might be a criticism)

How to use

Simply clone the repo and add the following to the json config of claude (or massage similarly for other clients) this:

{
    "connect4": {
      "command": "absolute path to uv",
      "args": [
        "--directory",
        "absolute path to this repo",
        "run",
        "main.py"
      ]
    }
}

Currently one can view the board by seeing the tool call from the chat of the LLM provider (should do better)...

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.