Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@YAPI MCP Server list all my configured YAPI projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
English | 中文
A Model Context Protocol (MCP) server for YAPI - enabling AI assistants to manage API documentation.
Tool | Description | YAPI API |
| List all configured projects | - |
| Run automated tests |
|
| Import API data |
|
| Add new interface |
|
| Save interface |
|
| Update interface |
|
| Get interface details |
|
| List interfaces |
|
| Get interface menu |
|
| Add interface category |
|
| Get all categories |
|
Related MCP server: YApi MCP Server
Clone the repository, then install dependencies and build in the project directory:
git clone <repo-url>
cd yapi-mcp
npm install
npm run buildVariable | Required | Description |
| Yes | YAPI server URL, e.g., |
| Yes | Project configuration in format: |
projectId1:token1,projectId2:token2Example:
123:abc123token,456:def456tokenYou can get the project token from YAPI project settings page.
Add to your Cursor MCP configuration file:
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"
}
}
}
}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"
}
}
}
}Add to your Claude Desktop configuration:
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"
}
}
}
}Edit %APPDATA%\Claude\claude_desktop_config.json with the same configuration, using your actual project path.
{
"name": "yapi_list_projects",
"arguments": {}
}{
"name": "yapi_interface_list",
"arguments": {
"page": 1,
"limit": 20
}
}{
"name": "yapi_interface_list",
"arguments": {
"project": 456,
"page": 1,
"limit": 20
}
}{
"name": "yapi_interface_add",
"arguments": {
"catid": 456,
"title": "Get User Info",
"path": "/api/user/info",
"method": "GET",
"desc": "Get user details by ID"
}
}{
"name": "yapi_interface_get",
"arguments": {
"id": 789
}
}{
"name": "yapi_run_auto_test",
"arguments": {
"project": 456,
"env_name": "dev"
}
}# Clone the repository
cd yapi-mcp
# Install dependencies
npm install
# Development mode
npm run dev
# Build
npm run build
# Run
npm startNever commit your YAPI tokens to version control
Use environment variables to store sensitive configuration
Consider using a secrets manager for production deployments
MIT
Contributions are welcome! Please feel free to submit a Pull Request.
导入接口数据到 YAPI
Inputs: type (required), json (required), url, project, +1 more.
新增接口
Inputs: catid (required), title (required), path (required), method (required), +12 more.
新增接口分类
Inputs: name (required), url, project, desc.
获取接口详情，可直接传入 YAPI 接口页面 URL 自动解析参数
Inputs: url, project, id.
获取接口列表
Inputs: url, project, catid, page, +1 more.
保存接口（新增或更新）
Inputs: catid (required), title (required), path (required), method (required), +13 more.
更新接口
Inputs: id (required), url, project, catid, +13 more.
列出所有已配置的 YAPI 项目
Inputs: no named parameters.
运行 YAPI 自动化测试
Inputs: url, project, env_name.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 11 tools
The tools have clear distinctions for core operations like add, get, list, and save, but there is significant overlap between yapi_interface_add and yapi_interface_save (which handles both add and update), and between yapi_interface_list and yapi_interface_list_menu (both list interfaces with slight variations). This overlap could cause confusion for agents when selecting the appropriate tool.
Most tools follow a consistent yapi_verb_noun pattern (e.g., yapi_interface_add, yapi_interface_get), with clear prefixes and snake_case throughout. However, there are minor deviations like yapi_interface_up instead of yapi_interface_update, and yapi_run_auto_test uses 'run' while others use verbs like 'add' or 'get', slightly breaking the pattern.
With 11 tools, this server is well-scoped for managing YAPI interfaces and projects. The count aligns with the domain's needs, covering operations for projects, interfaces, categories, and testing without being overwhelming or too sparse.
The toolset provides strong coverage for YAPI management, including CRUD operations for interfaces and categories, project listing, and automated testing. A minor gap is the lack of explicit tools for deleting interfaces or categories, which might require workarounds, but core workflows are well-supported.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Create and manage test cases, test runs and results in Testiny from your AI assistant.
Query and update Teable records, manage tables, and access the Teable API with AI agents.
Versioned documentation registry and semantic search for AI tools and coding assistants.
