
Frontend Code Analysis MCP
Analyzes frontend project code (React, Vue, Angular) and converts it into AI-understandable flow diagrams and object structures. Provides tools for code analysis, variable/function/component inspection, and project structure insights.
README
前端逻辑转AI理解MCP开发框架
基于Model Context Protocol (MCP)的前端代码分析工具开发框架,用于将前端项目的代码逻辑转换为AI易于理解的流程图和对象结构。
🚀 特性
- 完整的MCP协议实现 - 支持工具调用和资源访问
- 强大的代码分析能力 - 支持React、Vue、Angular等主流框架
- 类型安全 - 完整的TypeScript类型定义
- 模块化设计 - 清晰的架构和可扩展的模块
- 完善的测试框架 - 单元测试和集成测试支持
- 开发工具集成 - ESLint、Prettier、Jest等工具配置
📁 项目结构
frontend-analysis-mcp/
├── src/ # 源代码目录
│ ├── analyzer/ # 代码分析器
│ │ ├── FrontendCodeAnalyzer.ts
│ │ ├── VariableTracker.ts
│ │ ├── FunctionAnalyzer.ts
│ │ └── ComponentAnalyzer.ts
│ ├── server/ # MCP服务器
│ │ ├── FrontendAnalysisMCPServer.ts
│ │ ├── ToolHandler.ts
│ │ └── ResourceHandler.ts
│ ├── types/ # 类型定义
│ │ ├── ProjectInfo.ts
│ │ ├── VariableInfo.ts
│ │ ├── FunctionInfo.ts
│ │ ├── ComponentInfo.ts
│ │ └── errors.ts
│ ├── utils/ # 工具函数
│ │ ├── fileUtils.ts
│ │ ├── astUtils.ts
│ │ ├── typeUtils.ts
│ │ ├── logger.ts
│ │ └── errorHandler.ts
│ └── index.ts # 入口文件
├── tests/ # 测试目录
│ ├── unit/ # 单元测试
│ ├── integration/ # 集成测试
│ └── fixtures/ # 测试数据
├── examples/ # 示例目录
├── docs/ # 文档目录
├── .vscode/ # VS Code配置
├── package.json
├── tsconfig.json
├── jest.config.js
├── .eslintrc.js
├── .prettierrc
└── README.md
🛠️ 安装和设置
环境要求
- Node.js >= 18.0.0
- npm >= 8.0.0
- TypeScript >= 5.2.0
安装依赖
npm install
开发脚本
# 开发模式运行
npm run dev
# 构建项目
npm run build
# 运行测试
npm run test
# 运行测试并生成覆盖率报告
npm run test:coverage
# 代码检查
npm run lint
# 代码格式化
npm run format
# 类型检查
npm run type-check
🚀 快速开始
基本使用
import { FrontendAnalysisMCPServer } from './src/server/index.js';
import { FrontendCodeAnalyzer } from './src/analyzer/index.js';
// 创建MCP服务器
const server = new FrontendAnalysisMCPServer();
// 创建代码分析器
const analyzer = new FrontendCodeAnalyzer('/path/to/your/project');
// 设置分析器
server.setAnalyzer(analyzer);
// 启动服务器
await server.run();
分析项目
import { FrontendCodeAnalyzer } from './src/analyzer/index.js';
const analyzer = new FrontendCodeAnalyzer('/path/to/your/project');
const projectInfo = await analyzer.analyzeProject();
console.log('项目信息:', projectInfo);
console.log('框架类型:', projectInfo.framework);
console.log('文件数量:', projectInfo.files.length);
console.log('变量数量:', projectInfo.stats.totalVariables);
🔧 MCP工具
可用工具
- analyze_project - 分析整个项目
- get_variable_info - 获取特定变量信息
- get_function_info - 获取特定函数信息
- get_component_info - 获取特定组件信息
- generate_flow_diagram - 生成流程图
- search_code - 搜索代码
工具使用示例
// 分析项目
const result = await toolHandler.handleToolCall('analyze_project', {
projectPath: '/path/to/project',
framework: 'react'
});
// 获取变量信息
const variableInfo = await toolHandler.handleToolCall('get_variable_info', {
variableName: 'count',
filePath: '/path/to/file.jsx'
});
📊 MCP资源
可用资源
- project://structure - 项目结构信息
- project://variables - 变量信息
- project://functions - 函数信息
- project://components - 组件信息
- project://dependencies - 依赖信息
- project://statistics - 统计信息
资源访问示例
// 获取项目结构
const structure = await resourceHandler.handleResourceRead('project://structure');
// 获取所有变量
const variables = await resourceHandler.handleResourceRead('project://variables');
🧪 测试
运行测试
# 运行所有测试
npm run test
# 运行测试并监听文件变化
npm run test:watch
# 运行测试并生成覆盖率报告
npm run test:coverage
测试结构
tests/unit/
- 单元测试tests/integration/
- 集成测试tests/fixtures/
- 测试数据
📝 开发指南
代码规范
- 使用TypeScript进行类型安全开发
- 遵循ESLint和Prettier配置
- 编写完整的JSDoc注释
- 保持函数和类的单一职责
添加新功能
- 在相应的模块中添加新功能
- 更新类型定义
- 添加单元测试
- 更新文档
调试
使用VS Code调试配置:
- 打开VS Code
- 按F5启动调试
- 选择"Debug MCP Server"配置
📚 文档
详细的文档请参考 docs/
目录:
🤝 贡献
- Fork项目
- 创建功能分支 (
git checkout -b feature/AmazingFeature
) - 提交更改 (
git commit -m 'Add some AmazingFeature'
) - 推送到分支 (
git push origin feature/AmazingFeature
) - 打开Pull Request
📄 许可证
本项目采用MIT许可证 - 查看 LICENSE 文件了解详情。
🙏 致谢
- Model Context Protocol - MCP协议规范
- Babel - JavaScript解析和转换
- TypeScript - 类型安全的JavaScript
- Jest - JavaScript测试框架
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.