MCP Tic-Tac-Toe

A Model Context Protocol server for playing and analyzing tic-tac-toe games through standardized tool interfaces.

Stars

Forks

Watchers

Issues

MCP Tic-Tac-Toe is a server implementation that provides a complete set of MCP tools for playing, managing, and analyzing tic-tac-toe games. It supports interactions with AI assistants such as Claude, enabling features like creating multiple parallel sessions, making moves, providing strategic analysis, and managing game context. The server is designed for easy integration with clients through various transport methods, including stdio and SSE, and supports seamless AI-human collaboration.

Key Features

Implements MCP server for tic-tac-toe

Create, reset, and list multiple game sessions

Make and track game moves

Analyze board positions for strategic play

Get current board state and available moves

Check live game status and determine winner

Support for both AI and human players

Multiple transport methods: stdio, SSE, HTTP

Easy integration with Claude Code and MCP clients

Configurable server setup for cross-platform use

Use Cases

Demonstrating AI-human collaboration in board games

Integrating standardized game tools into AI assistants

Providing automated tic-tac-toe analysis and suggestions

Enabling multiple simultaneous tic-tac-toe sessions for users

Developing AI strategies through game session management

Showcasing MCP server integration in educational tools

Testing and developing model tools for context-driven interactions

Enabling peer-to-peer competitive gameplay with AI observers

Offering plug-and-play tic-tac-toe tools for code assistants

Facilitating research in game analysis and AI move prediction

README

MCP Tic-Tac-Toe

A Model Context Protocol (MCP) server that enables AI assistants to play tic-tac-toe through standardized tool interfaces. Perfect for demonstrating AI-human collaboration and MCP integration.

Overview

This project implements a complete tic-tac-toe game as an MCP server, allowing AI assistants like Claude to:

Create and manage multiple game sessions
Make strategic moves and analyze positions
Provide game commentary and suggestions
Play against humans or other AIs

Quick Start

Prerequisites

Go 1.19+ installed
Claude Code or other MCP-compatible client

Installation

bash

git clone https://github.com/tomholford/mcp-tic-tac-toe
cd mcp-tic-tac-toe
go mod tidy
go build -o bin/server cmd/server.go

Basic Usage

bash

# Start MCP server (stdio transport)
./bin/server

# Or specify transport method
./bin/server -transport=sse -addr=:8080

MCP Configuration

Claude Code Setup

Build the server:
bash
```
go build -o bin/server cmd/server.go
```

Add to your MCP configuration:

Create or edit your MCP configuration file:

bash

# For macOS/Linux
~/.config/claude-code/mcp_servers.json

# For Windows  
%APPDATA%\claude-code\mcp_servers.json

Add the server configuration:

json

{
  "mcpServers": {
    "tic-tac-toe": {
      "command": "/full/path/to/mcp-tic-tac-toe/bin/server",
      "args": ["-transport=stdio"],
      "env": {}
    }
  }
}

Restart Claude Code and the tic-tac-toe tools will be available. c

Claude Desktop

json

"tic-tac-toe": {
  "command": "/full/path/to/mcp-tic-tac-toe/bin/server",
  "args": [""]
}

Available MCP Tools

The server exposes 8 tools for complete game management:

Game Management

new_game - Create a new tic-tac-toe game
- Optional: game_id (string) - Custom game identifier
- Returns: Game ID, starting player, initial board
list_games - Show all active game sessions
- Returns: List of active game IDs
reset_game - Reset a game to initial state
- Required: game_id (string)
- Returns: Confirmation and fresh board

Gameplay

make_move - Execute a move on the board
- Required: game_id (string), position (A1-C3), player (X/O)
- Returns: Updated board, game status, next player
get_board - Get current board state
- Required: game_id (string)
- Returns: Board display, current player, move count
get_available_moves - List all valid moves
- Required: game_id (string)
- Returns: Available positions for current player

Analysis

get_status - Check game status and winner
- Required: game_id (string)
- Returns: Game status (ongoing/won/draw), winner if applicable
analyze_position - Get strategic analysis
- Required: game_id (string)
- Returns: Position analysis and board state

Usage Examples

Start a New Game

AI: Use the new_game tool
→ New game created with ID: game-a1b2c3d4
  Starting player: X
  Initial board:
    A B C
  1 · · ·
  2 · · ·  
  3 · · ·

Make Strategic Moves

Human: I'll take the center
AI: Use make_move tool with {"game_id": "game-a1b2c3d4", "position": "B2", "player": "X"}

AI: Let me analyze the position first
AI: Use analyze_position tool → Shows current state and opportunities

AI: I'll take a corner for strategic advantage  
AI: Use make_move tool with {"game_id": "game-a1b2c3d4", "position": "A1", "player": "O"}

Get Game Status

AI: Use get_status tool → Game Status: Ongoing, Current player: X, Move count: 2
AI: Use get_available_moves tool → Available moves (7): A2, A3, B1, B3, C1, C2, C3

Transport Options

The server supports three transport methods:

1. Stdio (Default)

Best for local MCP clients like Claude Code:

bash

./bin/server -transport=stdio

2. Server-Sent Events (SSE)

For web applications and real-time updates:

bash

./bin/server -transport=sse -addr=:8080

3. Streamable HTTP

For traditional HTTP integrations:

bash

./bin/server -transport=http -addr=:8080

Development

Project Structure

mcp-tic-tac-toe/
├── cmd/
│   ├── server.go          # MCP server main entry point
│   └── demo.go            # Game logic demonstration  
├── game/                  # Core tic-tac-toe logic
│   ├── types.go           # Game data structures
│   ├── engine.go          # Game rules and validation
│   └── engine_test.go     # Game logic tests
├── server/                # MCP server implementation  
│   ├── server.go          # MCP server setup and tools
│   ├── handlers.go        # Tool request handlers
│   └── server_test.go     # MCP integration tests
└── bin/                   # Built executables

Running Tests

bash

# Test all packages
go test ./game ./server -v

# Test specific functionality
go test ./game -run TestWinConditions
go test ./server -run TestMakeMoveTool

Building from Source

bash

# Build server
go build -o bin/server cmd/server.go

# Build demo
go build -o bin/demo cmd/demo.go

# Run demo (no MCP required)
./bin/demo

Resources

MCP Specification - Official MCP documentation
mcp-go Library - Go MCP implementation used in this project

Star History

Repository Owner

tomholford

User

Repository Details

Language Go

Default Branch master

Size 6,539 KB

Contributors 1

MCP Verified Nov 12, 2025

Programming Languages

100%

Topics

game go golang mcp mcp-server tic-tac-toe

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

Related MCPs

Discover similar Model Context Protocol servers

mcp-miro

Model Context Protocol server for integrating MIRO Whiteboard with AI workflows.

mcp-miro is a Model Context Protocol (MCP) compliant server that connects the MIRO Whiteboard Application to AI-based systems, such as Claude Desktop. It enables board manipulation, sticky note creation, bulk operations, and more through standardized MCP interfaces. Users can authenticate via OAuth and interact with MIRO boards programmatically for collaborative whiteboarding and automation tasks. The server can be installed using Smithery or mcp-get and supports debugging with the MCP Inspector.

⭐ 97
MCP
evalstate/mcp-miro

TickTick MCP Server

Enable powerful AI-driven task management for TickTick via the Model Context Protocol.

TickTick MCP Server provides comprehensive programmatic access to TickTick task management features using the Model Context Protocol. Built on the ticktick-py library, it enables AI assistants and MCP-compatible applications to create, update, retrieve, and filter tasks with improved precision and flexibility. The server supports advanced filtering, project and tag management, subtask handling, and robust context management for seamless AI integration.

⭐ 35
MCP
jen6/ticktick-mcp

RAE Model Context Protocol (MCP) Server

An MCP server enabling LLMs to access RAE’s dictionary and linguistic resources.

Provides a Model Context Protocol (MCP) server implementation for the Royal Spanish Academy API, facilitating integration with language models. Offers tools such as search and word information retrieval, exposing RAE’s dictionary and linguistic data to LLMs. Supports multiple transports including stdio and SSE, making it suitable for both direct and server-based LLM interactions.

⭐ 3
MCP
rae-api-com/rae-mcp

mcp-time

A Model Context Protocol server for time and date operations

mcp-time is a Model Context Protocol (MCP) server that enables AI assistants and MCP clients to perform standardized time and date-related operations. It provides natural language parsing for relative time expressions, supports flexible formatting, and allows manipulation and comparison of times. The server offers multiple integration methods, including stdio, HTTP stream, Docker, and npx for compatibility with various clients. It is designed for robust time handling and easy integration with AI tools.

⭐ 8
MCP
TheoBrigitte/mcp-time

MCP Zotero

Model Context Protocol server for seamless Zotero integration with AI tools.

MCP Zotero provides a Model Context Protocol server enabling AI models such as Claude to access and interact with Zotero libraries. Users can securely link their Zotero accounts and perform actions including listing collections, retrieving papers, searching the library, and getting details about specific items. Integration is designed for both standalone operation and as an extension for tools like Claude Desktop.

⭐ 137
MCP
kaliaboi/mcp-zotero

TripGo MCP Server

Remote MCP server providing transport location, departure, and routing tools via the TripGo API.

TripGo MCP Server acts as a remote Model Context Protocol server that wraps the TripGo API, offering tools for retrieving transport-related locations, departures from transport stops, multi-modal trip planning, and trip URL retrieval. It is deployed on Cloudflare Workers and is accessible directly or via MCP-compatible clients such as Claude Desktop through the mcp-remote proxy. The server supports direct integration for context-aware transport queries and trip management, facilitating enhanced interactions with public transport data.

⭐ 2
MCP
skedgo/tripgo-mcp-server

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

MCP Tic-Tac-Toe

Key Features

Use Cases

README

MCP Tic-Tac-Toe

Overview

Quick Start

Prerequisites

Installation

Basic Usage

MCP Configuration

Claude Code Setup

Claude Desktop

Available MCP Tools

Game Management

Gameplay

Analysis

Usage Examples

Start a New Game

Make Strategic Moves

Get Game Status

Transport Options

1. Stdio (Default)

2. Server-Sent Events (SSE)

3. Streamable HTTP

Development

Project Structure

Running Tests

Building from Source

Resources

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Topics

Related MCPs