Yudao Pilot MCP
中文 | English
中文
Yudao Pilot MCP 是面向 yudao / ruoyi-vue-pro 生态的工作区感知型 MCP 服务。它帮助 AI 编码工具识别本地后端、前端、数据库和代码生成目标,让 AI 生成的代码准确落到正确项目结构里。
严肃声明
yudao、ruoyi-vue-pro 生态与 ruoyi / RuoYi / 若依原生生态不是同一个项目。当前 MCP 只支持 yudao、ruoyi-vue-pro、ruoyi-vue-pro-jdk17、yudao-cloud 相关项目,不支持若依原生生态项目。
核心价值
- 让 AI 不再猜 yudao 项目目录和生成位置
- 用
.yudao-pilot/config.yaml固化后端、前端和数据库配置 - 基于项目指纹校验路径,避免代码写错仓库或模块
- 生成菜单、字典、H2 测试 SQL 和前后端骨架代码
- 当工作目录不明确时停止初始化,并要求 AI 先询问真实项目目录
快速使用
- 安装命令行入口。
git clone https://github.com/woodynew/yudao-pilot-mcp.git
cd yudao-pilot-mcp
uv tool install .
- 在 MCP 客户端中注册服务。
{
"mcpServers": {
"yudao-pilot": {
"command": "yudao-pilot",
"args": []
}
}
}
在你的 yudao 工作区中让 AI 先调用
load_workspace_config。首次使用会生成.yudao-pilot/config.yaml,并要求确认识别到的后端和前端路径。确认配置后,典型流程是:
load_workspace_config
validate_workspace_projects
inspect_codegen_context
generate_codegen_scaffold(write_files=true)
如果用户明确要求“先预览”,则调用:
generate_codegen_scaffold(write_files=false)
此时预览产物会写入 .yudao-pilot/previews/ 下的临时目录,不会影响项目现有代码。
文档
- 项目概览
- 配置指南
- MCP 工具与工作流
- SQL、菜单与字典生成
- 开发与测试
- 前端产物矩阵
- 产品说明
- 路线图
English
Yudao Pilot MCP is a workspace-aware MCP server for the yudao / ruoyi-vue-pro ecosystem. It helps AI coding tools understand local backend projects, frontend targets, database configuration, and code-generation routes so generated code lands in the right place.
Important Notice
The yudao / ruoyi-vue-pro ecosystem is not the same project as the original ruoyi / RuoYi ecosystem. This MCP currently supports yudao, ruoyi-vue-pro, ruoyi-vue-pro-jdk17, and yudao-cloud projects only. It does not support original RuoYi projects.
Core Value
- Stop AI tools from guessing yudao project paths
- Use
.yudao-pilot/config.yamlas the routing source of truth - Validate backend and frontend paths with project fingerprints
- Generate menu SQL, dictionary SQL, H2 test SQL, and backend/frontend scaffolds
- Refuse unsafe initialization when the project workspace is unknown
Quick Start
- Install the command.
git clone https://github.com/woodynew/yudao-pilot-mcp.git
cd yudao-pilot-mcp
uv tool install .
- Register the MCP server in your client.
{
"mcpServers": {
"yudao-pilot": {
"command": "yudao-pilot",
"args": []
}
}
}
Ask the AI client to call
load_workspace_configfrom your yudao workspace. On first use, Yudao Pilot creates.yudao-pilot/config.yamland asks the AI to confirm detected backend and frontend paths.After configuration is confirmed, the common flow is:
load_workspace_config
validate_workspace_projects
inspect_codegen_context
generate_codegen_scaffold(write_files=true)
If the user explicitly asks to preview first, call:
generate_codegen_scaffold(write_files=false)
Preview artifacts are written under .yudao-pilot/previews/ and do not touch the existing project code.
Documentation
- Overview
- Configuration
- MCP Tools and Workflow
- SQL, Menu, and Dictionary Generation
- Development and Testing
- Frontend Output Matrix
- Product Notes
- Roadmap