readyorai
ReadyOrAI
零成本 MCP 服务器,用于本地代码检查。分析你的代码是否符合整洁代码规范、最佳实践,并给出可操作的建议——无需修改代码,也无需调用 API。
功能特性
9 个分析器:复杂度、命名、结构、模式、导入、文档、安全、重复、AI 生成代码检测
多语言支持:JS/TS、Python、Go、Rust(深度分析)+ Java、C#、Ruby、PHP 等(基于正则)
零成本:所有分析均在本地运行——无需 API 密钥,无外部调用
MCP 服务器:通过 stdio 传输与 Claude Desktop、Claude Code 和 VS Code 配合使用
CLI 工具:
ready @filename和AI终端命令,可独立使用SARIF 输出:导出结果以集成 GitHub Code Scanning
监视模式:文件变更时持续重新分析
基线/差异模式:跟踪增量采用情况——只显示新问题
配置文件:项目级
.readyorai.json,用于共享设置行内抑制:使用
// readyorai-ignore注释静默特定发现
Related MCP server: Risk Audit MCP
安装
作为 MCP 服务器
Claude Desktop(claude_desktop_config.json):
{
"mcpServers": {
"readyorai": {
"command": "npx",
"args": ["-y", "readyorai"]
}
}
}Claude Code:
claude mcp add readyorai -- npx -y readyoraiVS Code(.vscode/mcp.json):
{
"servers": {
"readyorai": {
"command": "npx",
"args": ["-y", "readyorai"]
}
}
}作为 CLI 工具
npm install -g readyoraiCLI 用法
ready @src/index.ts # Inspect a single file
ready @src/ # Inspect a directory
ready @src/index.ts --checks security,naming # Run specific checks
ready @src/index.ts --json # JSON output
ready @src/index.ts --sarif # SARIF output (GitHub Code Scanning)
ready @src/index.ts --severity warning # Only warnings and errors
ready @src/index.ts --watch # Re-analyze on file changes
ready @src/ --baseline baseline.json # Compare against saved baseline
ready @src/ --save-baseline baseline.json # Save current results as baseline
AI # Inspect current directory
AI @src/utils.ts # Alias with file target退出码
代码 | 含义 |
| 未发现问题 |
| 发现警告 |
| 发现错误 |
| 运行时错误 |
配置
在项目根目录创建 .readyorai.json:
{
"checks": ["complexity", "naming", "security"],
"severity": "warning",
"exclude": ["dist/**", "node_modules/**"]
}行内抑制
在某一行的代码上静默特定发现:
eval(code); // readyorai-ignoreMCP 工具
工具 | 描述 |
| 分析单个文件的代码质量问题 |
| 批量分析目录中的所有源文件 |
| 获取定量指标(代码行数、复杂度、函数数量) |
| 比较两个文件版本,显示已修复、新引入或未变化的发现 |
| 为每个发现提供带上下文的可操作修复建议 |
MCP 提示词
提示词 | 描述 |
| 结构化代码审查,可指定关注领域 |
| 项目级健康评估 |
检查项
检查项 | 检测内容 |
| 圈复杂度/认知复杂度、深层嵌套 |
| 命名约定违规、单字母变量、布尔前缀 |
| 过长的文件/函数、参数过多、过长的行 |
| console.log、空 catch、魔法数字、嵌套三元表达式、TODO |
| 未使用的导入、通配符导入、分散的导入 |
| 缺少 JSDoc/文档字符串、注释比例过低 |
| 硬编码密钥、eval()、SQL 注入、XSS 模式 |
| 重复代码块、重复的魔法字符串 |
| 检测 AI 生成代码中常见的模式 |
语言支持
层级 | 语言 | 分析方式 |
1 | JavaScript、TypeScript、Python、Go、Rust | 完整的 AST 驱动分析 |
2 | Java、C#、Ruby、PHP、Swift、Kotlin、C、C++ | 正则 + 启发式分析 |
3 | 任意文本文件 | 基于行的检查(行长、TODO、密钥、重复) |
开发
git clone https://github.com/TedoNeObichaJavaScript/ReadyOrAI.git
cd ReadyOrAI
npm install
npm run build
npm test支持
如果你觉得 ReadyOrAI 有用,欢迎支持该项目:
Borko — 5 欧元
许可证
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
30+ deterministic dev and delivery tools: linting, metrics, diagrams, model advice, AI-text checks.
Deep security scans of repos you own from your editor: dependency CVEs, SAST, git-history secrets.
Detects database migration table locks, terraform cost leaks, and OWASP API flaws.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables comprehensive code analysis including quality assessment, security vulnerability detection, refactoring suggestions, complexity calculations, and automatic documentation generation for multiple programming languages.50MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables security scanning of code projects to identify common vulnerabilities like XSS, injections, SSRF, and path traversal issues. Provides local, offline scanning with severity-grouped results and actionable fix suggestions for improving code security.38 npm-
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered code safety analysis including risk detection, secret scanning, dependency checking, and code snapshot management. Works offline for basic features with optional cloud integration for advanced ML analysis and team collaboration.5 npm1Apache 2.0
- AlicenseAqualityAmaintenanceEnables AI assistants and developers to analyze code for language-specific best practices and idiomatic patterns across programming languages, CI automation, and configuration formats.1628 PyPI2MIT