idux-ui-mcp
Provides smart access to iDux UI component library, enabling AI assistants to retrieve component information, documentation, and usage examples via MCP tools.
README
idux-ui-mcp
idux-ui-mcp 是一个基于 Model Context Protocol (MCP) 的mcp服务,提供对 iDux UI 组件库的智能访问。本mcp服务允许开发者和 AI 助手更有效地检索 iDux 组件信息、文档和示例代码。
功能特性
Tools:
- list_idux_components: 获取所有可用的 idux 组件列表
- get_component_details: 获取特定 idux 组件的详细信息
- get_component_examples: 获取特定 idux 组件的使用示例
- search_components: 通过关键词搜索 idux 组件
- update_components_cache: 手动更新组件信息缓存
优势对比
相较于 RAG (Retrieval-Augmented Generation) 方案:
| 特性 | RAG 方案 | idux-ui-mcp |
|---|---|---|
| 数据新鲜度 | 依赖训练数据更新周期 | 可以实时从官方源获取 |
| 信息准确性 | 相似度匹配、信息不全 | 100% 精确匹配且信息完整 |
| 响应速度 | 向量检索耗时 | 本地缓存,毫秒级响应 |
| 版本控制 | 不支持 | 支持多版本切换 |
使用场景
场景一:开发使用idux-ui 的 web页面
实现一个TODO List应用,要求TODO项使用表格展示,UI组件使用idux
场景二:组件库问答
idux 的 pagination 组件如何实现分页总数自定义的效果
安装
使用npx
{
"mcpServers": {
"idux-ui-mcp": {
"command": "npx",
"args": ["-y", "idux-ui-mcp"]
}
}
}
环境变量配置:
| 环境变量 | 描述 | 必须 | 示例 | 默认值 |
|---|---|---|---|---|
| IDUX_ZIP_URL_VUE2 | Vue2 版本 zip 包下载地址(预留) | 否 | https://your.domain/idux-vue2.zip | - |
| IDUX_ZIP_URL_VUE3 | Vue3 版本 zip 包下载地址 | 否 | https://your.domain/idux-vue3.zip | https://github.com/IDuxFE/idux/archive/refs/heads/main.zip |
| DEFAULT_VUE_VERSION | 默认使用的Vue版本 | 否 | vue3 | vue3 |
| DOWNLOAD_TIMEOUT | 下载超时时间(毫秒) | 否 | 60000 | 60000 |
| LOG_LEVEL | 日志级别(debug/info/warn/error) | 否 | error | error |
{
"mcpServers": {
"idux-ui-mcp": {
"command": "...",
"args": ["..."],
"env": {
"DOWNLOAD_TIMEOUT": "60000",
"LOG_LEVEL": "error"
}
}
}
}
开发
# 构建项目
pnpm build
# 监视文件变更并自动重新构建
pnpm watch
# 运行测试
pnpm test
调试
使用 MCP Inspector 工具可以对服务器进行调试:
# 先构建项目
pnpm watch
npx @modelcontextprotocol/inspector node dist/index.js
缓存机制
组件信息缓存存储在用户目录下:
- macOS/Linux:
~/.idux-mcp/cache/ - Windows:
%USERPROFILE%\.idux-mcp\cache\
缓存清除也可以选择直接删掉上面的目录
日志
日志存放在缓存目录:~/.idux-mcp/logs/ or %USERPROFILE%\.idux-mcp\logs\
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.