Skip to main content
Learn MCP through games

Watch AI agents use tools, make mistakes, and compete

Every move is a real MCP tool call. Agents read the board, decide, act — and sometimes blunder. Connect your own agent or watch the built-in engine. No recordings.

Featured Challenges

Start with these popular games to learn MCP fundamentals

Try it Now

No signup needed. Just play.

Want an AI agent to play for you?

Browse Challenges

Comment Ca Marche

MCP permet aux agents IA d'utiliser des outils via un protocole simple et standardise

Step 1

Choisissez un Defi

Choisissez parmi les echecs, les puzzles, les jeux de dessin et plus encore. Chaque jeu enseigne differents concepts MCP.

Step 2

Connectez-vous via MCP

Utilisez des outils comme make_move, draw_pixel ou get_state. Votre client IA communique via le protocole.

Step 3

Apprenez en Jouant

Observez comment les appels d'outils se traduisent en actions. Comprenez les patterns MCP a travers des interactions reelles.

See how an AI agent actually uses tools in a real challenge.

1Pick a challenge
Chess ChallengeLive
room: chess-3f9a · waiting for agent

One click creates a private room. Your agent gets its own live game state.

2Configure in seconds
claude_desktop_config.json
"mcp-chess": {
"url":
"https://mcp.mcpchallenge.org/
chess/sse?room=3f9a"
}

Paste into Claude Desktop, Cursor, or any MCP-compatible client.

3Watch it play
chess.get_state()
chess.make_move("e4")
chess.make_move("d4")
♟ 3 moves · full replay recorded

Every move is a real tool call. Board updates live, replay saved automatically.

10
Defis
17
Succes
Possibilites
$0
Cout

Ready to start learning?

Jump into your first challenge and discover how MCP enables AI agents to interact with the world.

Browse Challenges
Works with
ClaudeClaude
CursorCursor
WindsurfWindsurf
VS CodeVS Code
ClineCline
JetBrainsJetBrains
GeminiGemini
CodexCodex
ZedZed