Module Craft
MCP server for standardizing software module development with tools for planning, code quality analysis, security scanning, performance evaluation, documentation generation, accessibility checks, and progress tracking.
README
Module Craft
Vision
Module Craft is a project designed to standardize and enhance the development of software modules through a robust quality control system. By leveraging a Model Control Protocol (MCP), Module Craft provides a set of tools and workflows to ensure that modules are well-planned, secure, performant, and well-documented, regardless of the development environment.
Core Concepts
The heart of Module Craft is an MCP that exposes a series of atomic "actions" that an AI agent can call. These actions cover the entire lifecycle of a module, from initial planning to final evaluation. This approach allows for the creation of standardized, automated, and intelligent workflows for module development.
Setup
- Install dependencies:
npm install
- Build the project:
npm run build
- Run in development mode:
npm run dev
Usage
This MCP server can be integrated with AI assistants that support the Model Context Protocol. The server provides the following tools:
Available Tools
plan_module- Generate detailed development plans from module descriptionsanalyze_code_quality- Analyze code for consistency, congruence, and static issuescheck_security_vulnerabilities- Scan for security vulnerabilities (planned)evaluate_performance- Analyze performance bottlenecks (planned)generate_documentation- Auto-generate code documentation (planned)check_accessibility- Check UI accessibility compliance (planned)validate_requirements- Validate implementation against requirements (planned)track_progress- Track development progress (planned)
Integration
To use this MCP server with an AI assistant, add it to your MCP configuration:
{
"mcpServers": {
"module-craft": {
"command": "node",
"args": ["dist/index.js"],
"cwd": "/path/to/module-craft"
}
}
}
Development
npm run dev- Run with hot reloadnpm run build- Build TypeScript to JavaScriptnpm run watch- Watch mode for development
Project Structure
src/
├── index.ts # Main MCP server
├── types.ts # TypeScript type definitions
└── actions/
├── planModule.ts # Module planning implementation
└── analyzeCodeQuality.ts # Code quality analysis
Currently Implemented
✅ plan_module - Fully functional module planning ✅ analyze_code_quality - Code consistency and static analysis
Planned Features
🚧 Security vulnerability scanning 🚧 Performance analysis 🚧 Documentation generation 🚧 Accessibility checking 🚧 Requirements validation 🚧 Progress tracking
MCP Actions
The following actions are available through the Module Craft MCP.
1. Module Planning & Definition
plan_module
- Description: Takes a high-level module description and generates a detailed development plan in Markdown format.
- Outputs:
- Functional and non-functional requirements.
- Use cases.
- Proposed file and directory structure.
- Potential external dependencies.
2. Quality Assurance
analyze_code_quality
- Description: Analyzes module code to ensure it adheres to best practices.
- Focus Areas:
- Code Consistency: Naming conventions, formatting.
- Congruence: Ensures code aligns with the initial plan.
- Static Analysis: Uses linters to detect common errors and dead code.
check_security_vulnerabilities
- Description: A dedicated security scanner.
- Capabilities:
- Scans for common vulnerability patterns (e.g., SQL injection, XSS).
- Checks project dependencies for known vulnerabilities.
evaluate_performance
- Description: Focuses on performance analysis.
- Capabilities:
- Identifies code bottlenecks.
- Analyzes algorithmic complexity.
- Recommends optimizations (e.g., efficient data structures, caching).
3. Documentation
generate_documentation
- Description: Automatically generates and maintains code documentation.
- Capabilities:
- Summaries: Creates overviews of a module's purpose and functionality.
- Function/Class Docs: Extracts docstrings to detail inputs, outputs, and purpose.
- Usage Examples: Generates code snippets demonstrating module usage.
- Gap Identification: Detects code sections lacking documentation.
4. Accessibility
check_accessibility
- Description: Ensures that UI-related modules are accessible to all users, including those with disabilities, by checking against standards like WCAG.
- Focus Areas:
- Semantic Validation: Correct use of HTML tags.
- ARIA Attributes: Proper implementation of ARIA for assistive technologies.
- Color Contrast: Ensures text is legible.
- Form Accessibility: Checks for proper labeling and clear instructions.
- Keyboard Navigation: Confirms all interactive elements are keyboard-accessible.
5. Module Evaluation & Progress Tracking
validate_requirements
- Description: Compares the implemented module against its initial requirements to ensure all functional and non-functional specifications have been met.
- Capabilities:
- Parses the
plan_moduleoutput. - Maps implemented features back to the requirements document.
- Identifies any deviations or unimplemented requirements.
- Parses the
track_progress
- Description: Provides an overview of the module's development status.
- Capabilities:
- Analyzes commit history and code changes to measure progress.
- Compares the current state against the proposed file structure and milestones.
- Generates a progress report, highlighting completed, in-progress, and pending tasks.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。