Swiftcode MCP Server
A Model Context Protocol server that automates code generation for web development, specializing in creating TypeScript API clients from Swagger/OpenAPI specs and Vue.js components for frontend development.
README
Swiftcode MCP Server
Project Overview
Swiftcode MCP Server is a Model Context Protocol (MCP) server that provides automatic code generation capabilities for modern web development. This server focuses on generating TypeScript API clients from Swagger/OpenAPI specifications and Vue.js components for rapid frontend development.
Features
- Swagger/OpenAPI to TypeScript: Automatically generate TypeScript API clients from Swagger specifications
- Vue Component Generation: Create complete Vue 3 list pages with filters, tables, and pagination
- Template Management: Access and utilize pre-built code generation templates
- Code Validation: Validate Swagger/OpenAPI specifications before generation
- Mock Data Generation: Optionally generate mock data for testing purposes
Tools
1. generate_api_client
Generate TypeScript API client from Swagger/OpenAPI specification.
Parameters:
swagger_url(string): URL to Swagger/OpenAPI JSON specificationswagger_content(string): Direct Swagger/OpenAPI JSON or YAML contentoutput_format(string): Output format ("typescript" or "javascript", default: "typescript")include_types(boolean): Whether to generate TypeScript type definitions (default: true)
Example:
{
"swagger_url": "https://api.example.com/swagger.json",
"output_format": "typescript",
"include_types": true
}
2. generate_vue_list
Generate Vue list page component with table and filters.
Parameters:
page_config(object): Page configuration with Chinese/English names and featuresfilters(object): Filter configuration for search functionalitytable_columns(object): Table column definitionsgenerate_mock(boolean): Whether to generate mock data (default: false)
Example:
{
"page_config": {
"cn": "用户管理",
"en": "userManagement",
"select": true,
"btn": ["新增", "删除"]
},
"filters": {
"用户名": "input",
"状态": "select",
"创建时间": "daterange"
},
"table_columns": {
"用户名": "text",
"邮箱": "text",
"创建时间": "time",
"操作": {
"type": "operate",
"render": ["编辑", "删除"]
}
}
}
3. get_templates
Get available code generation templates.
Parameters:
template_type(string): Type of templates to retrieve ("vue-list", "api-client", or "all")
4. validate_swagger
Validate Swagger/OpenAPI specification.
Parameters:
swagger_url(string): URL to Swagger/OpenAPI specificationswagger_content(string): Direct Swagger/OpenAPI content
Prompts
The server provides several helpful prompts:
swiftcode_getting_started: Introduction guide to Swiftcode featuresswagger_to_typescript: Detailed guide for Swagger to TypeScript conversionvue_component_generation: Vue component generation guide and best practicestroubleshooting: Common issues and troubleshooting guide
Supported Technologies
Frontend Frameworks
- Vue 3 with Composition API
- Element Plus UI components
- TypeScript support
API Specifications
- Swagger 2.0
- OpenAPI 3.0+
- JSON and YAML formats
Generated Code Features
- TypeScript interfaces and types
- Vue 3 reactive components
- Element Plus form and table components
- Pagination and filtering
- Mock data generation
Setup
NPX (Recommended)
Add to your MCP client configuration:
{
"mcpServers": {
"swiftcode-npm": {
"command": "npx",
"args": ["-y", "@swiftcode/mcp"]
}
}
}
Local Development
pnpm install
# 编译 mcp
ppm build
# 启动 mcp 调试器
pnpm inspector
Add to your MCP client configuration:
{
"mcpServers": {
// 本地开发
"swiftcode-local": {
"command": "node",
"args": ["swiftcode-mcp-server/dist/index.js"]
}
}
}
Docker
# Build Docker image
docker build -t swiftcode-mcp .
# Run container
docker run -it swiftcode-mcp
Usage Examples
Generate API Client from Swagger URL
// Use the generate_api_client tool
{
"swagger_url": "https://petstore.swagger.io/v2/swagger.json",
"output_format": "typescript",
"include_types": true
}
Generate Vue List Component
// Use the generate_sfc_client tool
{
"page_config": {
"cn": "产品列表",
"en": "productList",
"select": true,
"top": true,
"btn": ["新增产品", "批量删除"]
},
"filters": {
"产品名称": "input",
"分类": "select",
"价格范围": {
"type": "daterange",
"range": [1, "m"]
}
},
"table_columns": {
"选择": "select",
"序号": "index",
"产品名称": "text",
"价格": "text",
"创建时间": "date",
"操作": {
"type": "operate",
"fixed": "right",
"render": ["编辑", "删除", "查看详情"]
}
},
"generate_mock": true
}
Filter Types
input: Text input fieldselect: Dropdown selectiondaterange: Date range pickerdatetime: Date and time pickerdate: Date picker onlydatetimerange: Date and time range picker
Table Column Types
text: Plain text columntime/date: Formatted date/time columnselect: Selection checkbox columnindex: Auto-incrementing index columnoperate: Action buttons columnoption: Enum/status columnlink: Clickable link columntag: Tag/badge column
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
This project is licensed under the MIT License. See the LICENSE file for details.
Support
For questions, issues, or feature requests, please visit the GitHub repository or contact the development team.
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。