chess-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chess-mcpLet's play chess. You go first and show the board."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
♟ Chess MCP 国际象棋MCP服务器
一个开箱即用的国际象棋 MCP 服务器:AI 对弈、局面分析、走法验证,内置实时可视化棋盘——agent 通过 MCP 工具走的每一步棋,浏览器页面实时同步。
✨ 特性
🎯 6 个 MCP 工具:查看棋盘 / 走棋 / 合法走法 / 重置 / 历史 / 获取可视化地址
🖥️ 内置 Web 可视化棋盘,与 MCP 工具共享同一份棋局状态,WebSocket 实时同步
🚀 一条命令启动,Web 服务随 MCP 服务器自动拉起,无需单独部署
✅ 完整规则:走法校验、将军/将杀判定、兵升变
Related MCP server: MCP Chrome Bridge
🚀 一键启动
git clone https://github.com/ShuiYi-bit/chess-mcp.git
cd chess-mcp
npm install
npm startMCP 模式:服务器通过 stdio 与 MCP 客户端通信,同时自动在
http://localhost:3000开启可视化棋盘可视化模式:Windows 直接双击
start.bat,服务启动后自动打开浏览器棋盘全局命令:
npm install -g .之后可在任意位置直接运行chess-mcp
端口占用时自动尝试 3001–3019,也可用环境变量 PORT 指定。
🔌 MCP 客户端配置
ZCode / Claude Desktop / Cursor 等
在 MCP 配置文件中加入(路径改为你的实际克隆路径):
{
"mcpServers": {
"chess": {
"command": "node",
"args": ["/path/to/chess-mcp/mcp-server.js"]
}
}
}ZCode 用户级:
~/.zcode/cli/config.json→mcp.serversClaude Desktop:
claude_desktop_config.json→mcpServers全局安装后也可以用
"command": "chess-mcp",无需写路径
🛠️ MCP 工具
工具 | 说明 | 参数 |
| 获取棋盘状态和局面信息 | 无 |
| 走棋 |
|
| 查看指定棋子的合法走法 |
|
| 重置棋局 | 无 |
| 走棋历史 | 无 |
| 获取可视化棋盘页面地址 | 无 |
♟️ 坐标格式
列:
a-h(左到右),行:1-8(下到上)示例:
e2= e 列第 2 行
💬 使用示例
用户: 我们下国际象棋,你执黑
AI: 调用 chess_status 查看棋盘 → 回复可视化棋盘地址 → 等待用户走棋
用户: 走 e2 到 e4
AI: 调用 chess_move(from="e2", to="e4") → 页面实时更新🖥️ Web 可视化棋盘
与 MCP 工具同一份棋局状态:agent 走棋,页面立即刷新;页面点击走棋,agent 也能看到
点击棋子高亮所有合法落点,显示被吃棋子和走棋记录
仅在 MCP 服务器运行期间可访问(MCP 客户端断开后进程自动退出并释放端口)
📁 项目结构
chess-mcp/
├── mcp-server.js # MCP 服务器(含内嵌 Web/WS 服务,唯一入口)
├── public/ # 可视化棋盘前端(原生 HTML/CSS/JS)
├── start.bat # Windows 一键启动
├── mcp-config.json # MCP 配置示例
└── package.json许可证
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Chess MCP for Claude: engine analysis, attack maps, game review. One URL, no install.
Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
Pedagogical chess intelligence for AI agents: explain positions and games for a target Elo.
MCP server exposing the Backtest360 engine API as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLets AI coding agents control and inspect a live Chrome browser via MCP, providing Chrome DevTools capabilities for automation, debugging, and performance analysis.11 npmApache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control Chrome browser actions like navigation, clicking, form filling, screenshots, and console/network logging via an MCP server and Chrome extension.897 npmMIT
- AlicenseAqualityCmaintenanceEnables AI agents to control a browser via MCP with structured perception, verified actions, and self-healing capabilities.1318 npm1MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that enables AI agents to control Chrome via DevTools CDP and accessibility trees, providing 21 tools for browser automation including tab management, navigation, interactions, and page capture.-