MCP Swagger Tools
Automatically parses Swagger/OpenAPI documentation, generates frontend code (Vue3, React, etc.), and enables API testing through natural language commands.
README
MCP Swagger Tools
<p align="center"> <img src="https://img.shields.io/badge/MCP-Swagger%20Tools-green" alt="MCP"> <img src="https://img.shields.io/badge/Python-3.10+-blue" alt="Python"> <img src="https://img.shields.io/badge/License-MIT-yellow" alt="License"> </p>
🤖 MCP (Model Context Protocol) 工具 - 自动解析 Swagger/OpenAPI 文档,生成前端代码,测试 API 接口
功能特性
🔧 配置管理
- 支持配置多个 Swagger 地址
- 支持多种鉴权方式:Basic Auth、Bearer Token、Cookie
- 自动校验配置有效性
📡 接口解析
- 自动解析 Swagger 2.0 / OpenAPI 3.0 文档
- 按模块/标签分组展示接口
- 支持搜索和筛选接口
- 解析结果缓存,避免重复请求
💬 对话式指令
- 自然语言理解指令
- 核心指令支持:
- "列出所有接口"
- "获取xxx接口"
- "封装xxx接口为Vue3代码"
- "生成xxx列表页"
- "测试xxx接口"
🎨 前端代码生成
- 支持 Vue3 (Composition API)、React、原生 JavaScript
- 自动生成 TypeScript 类型
- 包含请求拦截器和错误处理
- 可复制的代码片段
📄 页面生成
- 自动生成列表页、详情页、表单页
- 适配 Element Plus、Ant Design
- 包含搜索、分页、CRUD 操作
🧪 接口测试
- 在线测试解析后的接口
- 支持自定义参数和请求体
- 实时查看响应结果
快速开始
1. 安装
# 克隆项目
cd /path/to/workspace
# 创建虚拟环境
uv venv
source .venv/bin/activate
# 安装依赖
uv pip install -e .
2. 运行 MCP 服务器
# 激活虚拟环境
source .venv/bin/activate
# 启动服务器
python3 mcp_swagger_cli.py
3. 配置到 MCP 客户端
Trae 配置示例
{
"mcpServers": {
"swagger-tools": {
"command": "python3",
"args": ["/path/to/mcp-swagger-tools/mcp_swagger_cli.py"],
"env": {
"SWAGGER_URL": "https://petstore.swagger.io/v2/swagger.json",
"SWAGGER_NAME": "PetStore",
"SWAGGER_AUTH_TYPE": "none"
},
"cwd": "/path/to/mcp-swagger-tools"
}
}
}
Cursor 配置示例
{
"mcpServers": {
"swagger-tools": {
"command": "python3",
"args": ["/path/to/mcp-swagger-tools/mcp_swagger_cli.py"],
"env": {
"SWAGGER_URL": "http://your-api.com/swagger-ui.html",
"SWAGGER_NAME": "My API",
"SWAGGER_AUTH_TYPE": "bearer",
"SWAGGER_TOKEN": "your-token-here"
},
"cwd": "/path/to/mcp-swagger-tools"
}
}
}
环境变量配置
| 变量 | 说明 | 必填 | 示例 |
|---|---|---|---|
SWAGGER_URL |
Swagger 文档地址 | ✅ | http://localhost:8080/swagger-ui.html |
SWAGGER_NAME |
配置名称 | ❌ | My API |
SWAGGER_AUTH_TYPE |
鉴权方式 | ❌ | none, basic, bearer, cookie |
SWAGGER_USERNAME |
用户名 (basic auth) | ❌ | admin |
SWAGGER_PASSWORD |
密码 (basic auth) | ❌ | 123456 |
SWAGGER_TOKEN |
Token (bearer auth) | ❌ | eyJhbGciOiJIUzI1NiIs... |
SWAGGER_COOKIE |
Cookie (cookie auth) | ❌ | SESSION=abc123 |
鉴权方式配置示例
无鉴权:
{
"SWAGGER_URL": "http://localhost:8080/swagger-ui.html",
"SWAGGER_NAME": "Dev API",
"SWAGGER_AUTH_TYPE": "none"
}
Basic Auth:
{
"SWAGGER_URL": "http://localhost:8080/swagger-ui.html",
"SWAGGER_NAME": "Dev API",
"SWAGGER_AUTH_TYPE": "basic",
"SWAGGER_USERNAME": "admin",
"SWAGGER_PASSWORD": "admin123"
}
Bearer Token:
{
"SWAGGER_URL": "http://api.example.com/v3/api-docs",
"SWAGGER_NAME": "Production API",
"SWAGGER_AUTH_TYPE": "bearer",
"SWAGGER_TOKEN": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
}
Cookie:
{
"SWAGGER_URL": "http://api.example.com/swagger-ui.html",
"SWAGGER_NAME": "Internal API",
"SWAGGER_AUTH_TYPE": "cookie",
"SWAGGER_COOKIE": "JSESSIONID=abc123; UserID=admin"
}
MCP 工具列表
| 工具 | 说明 | 示例 |
|---|---|---|
list_configs |
列出所有配置 | list_configs |
add_config |
添加新配置 | add_config(url="...") |
delete_config |
删除配置 | delete_config(config_id=0) |
parse_swagger |
解析接口文档 | parse_swagger() |
search_endpoints |
搜索接口 | search_endpoints(query="user") |
generate_api_code |
生成 API 代码 | generate_api_code(endpoint_path="/api/users", method="get", framework="vue3") |
generate_page |
生成页面代码 | generate_page(endpoint_path="/api/users", method="get", page_type="list") |
test_endpoint |
测试接口 | test_endpoint(endpoint_path="/api/users", method="get") |
execute_command |
执行自然语言指令 | execute_command(command="列出所有接口") |
使用示例
列出所有接口
用户: 列出所有接口
助手: 📚 Swagger Petstore v1.0.7
🔗 https://petstore.swagger.io/v2
### pet (9 endpoints)
POST /pet/{petId}/uploadImage - uploads an image
POST /pet - Add a new pet to the store
PUT /pet - Update an existing pet
GET /pet/findByStatus - Finds Pets by status
...
生成前端代码
用户: 封装findByStatus接口为vue3代码
助手: ```typescript
// Swagger Petstore - API
// Generated by MCP Swagger Tools
import { ref } from 'vue'
import axios from 'axios'
const apiClient = axios.create({
baseURL: 'https://petstore.swagger.io/v2',
timeout: 30000,
...
```
生成页面
用户: 生成宠物列表页
助手: ```vue
<template>
<div class="findByStatus-page">
<!-- Table -->
<el-table :data="tableData" v-loading="loading" border>
...
```
测试接口
用户: 测试findByStatus接口
助手: ✅ Success (200, 1939ms)
```json
[
{"id": 1, "name": "doggie", "status": "available"},
{"id": 2, "name": "doggie 2", "status": "available"},
...
]
```
依赖
- Python >= 3.10
- mcp >= 1.0.0
- httpx >= 0.27.0
- openapi-spec-validator >= 0.7.0
- pyyaml >= 6.0
- jinja2 >= 3.1.0
项目结构
mcp-swagger-tools/
├── mcp_swagger/
│ ├── __init__.py # 包入口
│ ├── config.py # 配置管理
│ ├── parser.py # Swagger解析
│ ├── generator.py # 代码生成
│ ├── executor.py # API执行
│ ├── commands.py # 指令解析
│ └── server.py # MCP服务器
├── tests/ # 测试
├── pyproject.toml # 项目配置
├── README.md # 文档
└── LICENSE # MIT许可证
测试
# 运行测试
python3 -m pytest tests/ -v
# 运行特定测试
python3 -m pytest tests/test_core.py::TestCodeGenerator -v
License
MIT License - see LICENSE file for details
🤖 Generated by MCP Swagger Tools
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.