dafeiyu
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., "@dafeiyu来下盘中国象棋吧,我执红"
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.
dsh-chinese-chess
在 DeepSeek Harness 的右侧栏下中国象棋。你走一方,当前会话里的模型走另一方。棋子只在 MCP 工具 submit_move 成功时移动。对话和思维链都不是着法。
npm 包名仍是 dsh-dafeiyu-xiangqi。DeepSeek Harness 用这个名字加载插件;本仓库的名字是 dsh-chinese-chess。
安装
在要用的配置目录里安装,桌面端优先,例如 ~/.dsh/profiles/desktop。网页配置同样可以装,不要卸掉已有的侧栏包。
把
dsh-dafeiyu-xiangqi加进该配置package.json的dsh.profile.bundles。加上依赖并安装:
"dsh-dafeiyu-xiangqi": "github:VlanTech/dsh-chinese-chess"npm install完全退出 DeepSeek Harness,再打开。
cordis.patch.yml 会注册插件,并拉起名为 dafeiyu 的 MCP 服务。脚本路径按当前配置解析,不写死某一台机器的目录。
Related MCP server: Chess MCP Server
怎么下
输入
/chessplay,或在对话里说「来下棋」「下象棋」。棋盘出现在右侧栏。在开始界面选择「我执红」或「我执黑」。选中的一方画在下方。
在棋盘上走子会直接叫醒当前会话,不必再对模型说一次开始。
说「重来」「再来一局」「重新开始」「重开」或「新的一局」,回到选边。模型也可以调用
mcp__dafeiyu__restart_game做同样的事。选边之前它不能走子。轮到模型时,它先读
mcp__dafeiyu__read_position。坐标以模型自己的棋子在下方为准。它可以先用mcp__dafeiyu__preview_move看下一着会被吃掉哪些子,再提交唯一一着mcp__dafeiyu__submit_move。欲走不会显示在棋盘上。
局面写在 ~/.dsh/profiles/desktop/dafeiyu-xiangqi.json。桌面端和网页端共用这一份。
开发
node --test tests/*.test.js需要本机已安装 DeepSeek Harness 的命令行包。也可以用 DSH_PACKAGE_ROOT 指向别的安装位置。
许可
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.
Pit your LLM against rogue AI and rival models, or try to beat it yourself in hot seat. 3D tactics.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides an interactive chess game experience through MCP tools with a web-based chessboard interface. Enables users to play chess games, make moves using standard algebraic notation, and manage persistent game state across sessions.17 npm5Apache 2.0
- FlicenseBqualityDmaintenanceEnables AI assistants to play, analyze, and track chess games with full rule validation and support for standard algebraic notation. It provides tools for position evaluation and game state persistence during user sessions.2-
- FlicenseAqualityDmaintenanceEnables AI assistants to play chess against users, manage games, make moves, and visualize boards with Stockfish AI opponent.81-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to play and analyze chess, validate moves, and view a live synchronized visual board in the browser through MCP tools.17 npmMIT