ttt-mcp
Exposes tic-tac-toe game tools (new_game, get_state, make_move) for Claude to play against a human via chat.
README
ttt-mcp — Tic-Tac-Toe MCP Server
A minimal MCP server exposing a tic-tac-toe game as tools, intended to be played by Claude (via Claude Desktop) against a human via chat.
Tools exposed
new_game— reset to empty board, X to moveget_state— return current board + statusmake_move(row, col)— place the current player's mark; server alternates turns
Setup
cd ttt-mcp
npm install
npm run build
Wire it into Claude Desktop
Edit your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add (or merge into) this:
{
"mcpServers": {
"tic-tac-toe": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/ttt-mcp/dist/index.js"]
}
}
}
Replace the path with your actual absolute path. Then fully quit and restart Claude Desktop.
Verify it loaded
In Claude Desktop, open a new chat and look for the MCP tools indicator (slider/plug icon near the input). You should see tic-tac-toe listed with three tools.
If it's missing, check Claude Desktop's MCP logs:
- macOS:
~/Library/Logs/Claude/mcp*.log
Test outside Claude Desktop
You can poke the server directly with the official inspector:
npm run inspect
This launches a web UI that lets you call the tools manually — handy for debugging.
Playing
In Claude Desktop chat, just say: "Let's play tic-tac-toe. You start."
I'll call new_game, make a move, and we go from there. When it's your turn, tell me your move ("row 1 column 2") and I'll call make_move on your behalf, then take my own turn.
What to add next
- Per-conversation game state (currently single global state)
- AI difficulty levels (right now I just decide moves myself in chat)
- Replay history / undo
- Multiple game rooms
- Web frontend that subscribes to state changes
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.