Auto API - YApi
A tool to retrieve API interface information from YApi, with authentication configurable via environment variables.
YApi MCP 服务
一个基于 Model Context Protocol (MCP) 的 YApi 接口信息获取工具
🚀 功能特性
- 📋 接口列表获取: 根据 YApi 分类页面 URL 获取接口列表
- 📝 接口详情获取: 根据接口 ID 获取详细的请求/响应体信息
- 🔧 环境变量支持: 支持通过环境变量配置认证信息
- 🛡️ 错误处理: 完善的错误处理和用户友好的错误提示
本地开发
git clone https://github.com/twelve-web/yapi-mcp.git
cd yapi-mcp
npm install
npm run build
🔧 配置
创建 .env 文件并添加 YApi 认证信息(可选):
YAPI_TOKEN=""
BASE_URL=""
版本
node>18
npm 官方源
🎯 在 MCP 客户端中使用
Cursor Desktop 配置
在 mcp.json 中添加:
{
"mcpServers": {
"auto-yapi-mcp": {
"command": "npx",
"args": ["-y", "auto-yapi-mcp"],
"env": {
"YAPI_TOKEN": "aa270a5a35f043540xxxxxxx5c908164f6fcae",
"BASE_URL": "https://fed.xxxx.com"
}
}
}
}
📸 参数获取方式

🛠️ 可用工具
1. yapi_get_interfaces
获取指定分类下的接口列表
参数:
url(string): YApi 分类页面 URL,格式如https://xxxxx.com/project/810/interface/api/cat_2783
示例:
工具: yapi_get_interfaces
参数: url = "https://xxxxx.com/project/810/interface/api/cat_2783"
2. yapi_get_interface_detail
获取指定接口的详细信息(请求体和响应体)
参数:
id(string): 接口 ID,来自接口列表中的_id字段
示例:
工具: yapi_get_interface_detail
参数: https://xxxxxxx/project/1219/interface/api/42726
📖 使用流程
- 获取接口列表: 使用
yapi_get_interfaces获取分类下的所有接口 - 获取接口详情: 使用
yapi_get_interface_detail获取详细信息 - 生成类型定义: 基于返回的请求/响应体生成 TypeScript 类型

📄 License
MIT
🤝 贡献
欢迎提交 Issue 和 Pull Request!
📧 联系
如有问题,请提交 Issue 或联系作者。
Related Servers
Jupyter Earth MCP Server
Provides tools for geospatial analysis within Jupyter notebooks.
Gemini CLI MCP Server
An MCP server and CLI wrapper for Google's Gemini CLI, featuring OAuth authentication support.
GraphQL MCP
Interact with GraphQL APIs using LLMs. Supports schema introspection and query execution.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
Vibe Stack MCP
Helps developers choose the right tech stack for their projects with personalized recommendations.
MAVAE - IMAGE TOOLBOX
A creative toolkit for AI agents to generate, edit, and manage images, models, and collections using the MAVAE API.
Project Atlantis
A Python MCP host server that allows for dynamic installation of functions and third-party MCP tools.
MCP-Logic
Provides automated reasoning for AI systems using the Prover9 and Mace4 theorem provers.
Databutton
An MCP server for initial app planning and creating a good starting point for an app.
Agentic Control Framework (ACF)
A toolkit for autonomous agent development with tools for task management, filesystem operations, browser automation, and terminal control.