YAPI MCP Server
Enables AI assistants to manage YAPI API documentation by providing tools to create, update, and retrieve interface details. It also supports running automated tests and managing API data across multiple configured projects.
README
YAPI MCP Server
English | 中文
A Model Context Protocol (MCP) server for YAPI - enabling AI assistants to manage API documentation.
Features
| Tool | Description | YAPI API |
|---|---|---|
yapi_list_projects |
List all configured projects | - |
yapi_run_auto_test |
Run automated tests | /api/open/run_auto_test |
yapi_import_data |
Import API data | /api/open/import_data |
yapi_interface_add |
Add new interface | /api/interface/add |
yapi_interface_save |
Save interface | /api/interface/save |
yapi_interface_up |
Update interface | /api/interface/up |
yapi_interface_get |
Get interface details | /api/interface/get |
yapi_interface_list |
List interfaces | /api/interface/list |
yapi_interface_list_menu |
Get interface menu | /api/interface/list_menu |
yapi_interface_add_cat |
Add interface category | /api/interface/add_cat |
yapi_interface_get_cat_menu |
Get all categories | /api/interface/getCatMenu |
Installation
Clone the repository, then install dependencies and build in the project directory:
git clone <repo-url>
cd yapi-mcp
npm install
npm run build
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
YAPI_BASE_URL |
Yes | YAPI server URL, e.g., https://yapi.example.com |
YAPI_PROJECTS |
Yes | Project configuration in format: projectId1:token1,projectId2:token2 |
YAPI_PROJECTS Format
projectId1:token1,projectId2:token2
Example:
123:abc123token,456:def456token
You can get the project token from YAPI project settings page.
Usage with Cursor
Add to your Cursor MCP configuration file:
macOS/Linux
Edit ~/.cursor/mcp.json and replace /path/to/yapi-mcp with your actual project path:
{
"mcpServers": {
"yapi": {
"command": "node",
"args": ["/path/to/yapi-mcp/dist/index.js"],
"env": {
"YAPI_BASE_URL": "https://your-yapi-server.com",
"YAPI_PROJECTS": "123:your-token-here,456:another-token"
}
}
}
}
Windows
Edit %APPDATA%\Cursor\mcp.json and use your actual project path (e.g. C:\\Users\\YourName\\yapi-mcp\\dist\\index.js):
{
"mcpServers": {
"yapi": {
"command": "node",
"args": ["C:\\path\\to\\yapi-mcp\\dist\\index.js"],
"env": {
"YAPI_BASE_URL": "https://your-yapi-server.com",
"YAPI_PROJECTS": "123:your-token-here"
}
}
}
}
Usage with Claude Desktop
Add to your Claude Desktop configuration:
macOS
Edit ~/Library/Application Support/Claude/claude_desktop_config.json and replace /path/to/yapi-mcp with your actual project path:
{
"mcpServers": {
"yapi": {
"command": "node",
"args": ["/path/to/yapi-mcp/dist/index.js"],
"env": {
"YAPI_BASE_URL": "https://your-yapi-server.com",
"YAPI_PROJECTS": "123:your-token-here"
}
}
}
}
Windows
Edit %APPDATA%\Claude\claude_desktop_config.json with the same configuration, using your actual project path.
Tool Examples
List All Projects
{
"name": "yapi_list_projects",
"arguments": {}
}
Get Interface List (Default Project)
{
"name": "yapi_interface_list",
"arguments": {
"page": 1,
"limit": 20
}
}
Get Interface List (Specific Project)
{
"name": "yapi_interface_list",
"arguments": {
"project": 456,
"page": 1,
"limit": 20
}
}
Add New Interface
{
"name": "yapi_interface_add",
"arguments": {
"catid": 456,
"title": "Get User Info",
"path": "/api/user/info",
"method": "GET",
"desc": "Get user details by ID"
}
}
Get Interface Details
{
"name": "yapi_interface_get",
"arguments": {
"id": 789
}
}
Run Automated Tests
{
"name": "yapi_run_auto_test",
"arguments": {
"project": 456,
"env_name": "dev"
}
}
Development
# Clone the repository
cd yapi-mcp
# Install dependencies
npm install
# Development mode
npm run dev
# Build
npm run build
# Run
npm start
Security
- Never commit your YAPI tokens to version control
- Use environment variables to store sensitive configuration
- Consider using a secrets manager for production deployments
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
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。
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。
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。
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。
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。
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。
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。