A
licenseC
qualityD
maintenanceA Model Context Protocol server that enables AI agents to generate, fetch, and manage UI components through natural language interactions.
3
40 npm
7
ISC
Shadcn UI MCP Server
by heilgar
Shadcn UI MCP 服务器
强大而灵活的 MCP（模型控制协议）服务器，旨在提升 Shadcn UI 组件的开发体验。该服务器通过先进的工具和功能，为构建和管理 UI 组件奠定了坚实的基础。
特征
工具
MCP 服务器提供了一组可通过模型控制协议使用的工具：
list-components：获取可用的 shadcn/ui 组件列表get-component-docs：获取特定组件的文档install-component：安装 shadcn/ui 组件list-blocks：获取可用 shadcn/ui 块的列表get-block-docs：获取特定块的文档install-blocks：安装 shadcn/ui 块
功能
组件管理
列出可用的 shadcn/ui 组件
获取特定组件的详细文档
安装支持多种包管理器（npm、pnpm、yarn、bun）的组件
区块管理
列出可用的 shadcn/ui 块
获取特定块的文档和代码
安装支持多个包管理器的块
包管理器支持
为 npm、pnpm、yarn 和 bun 提供灵活的运行时支持
自动检测用户首选的包管理器
Related MCP server: aceternityui-mcp
安装
先决条件
Node.js（v18 或更高版本）
npm 或 yarn 包管理器
Claude桌面配置
要与 Claude Desktop 一起使用，请添加服务器配置：
在 MacOS 上： ~/Library/Application Support/Claude/claude_desktop_config.json在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}风帆冲浪配置
将其添加到您的./codeium/windsurf/model_config.json ：
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}游标配置
将其添加到您的.cursor/mcp.json中：
{
"mcpServers": {
"shadcn-ui-server": {
"command": "npx",
"args": ["@heilgar/shadcn-ui-mcp-server"]
}
}
}开发与调试
本地开发
安装依赖项：
npm install构建服务器：
npm run build调试
由于 MCP 服务器通过 stdio 进行通信，调试起来可能比较困难。我们建议使用MCP Inspector进行调试：
npm run inspector检查器将提供一个 URL 来访问浏览器中的调试工具，允许您：
监控 MCP 通信
检查工具调用和响应
调试服务器行为
查看实时日志
相关项目和依赖项
该项目使用以下工具和库构建：
模型上下文协议 TypeScript SDK - MCP 服务器和客户端的官方 TypeScript SDK
MCP Inspector - MCP 服务器的调试工具
Cheerio - 专为服务器设计的核心 jQuery 的快速、灵活、精简实现
执照
MIT 许可证 - 您可以自由地将此项目用于您自己的目的。
贡献
欢迎贡献代码！欢迎提交 Pull 请求。
Available Tools
6 toolsget-block-docsD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| block | Yes | Name of the block to get documentation for |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get-component-docsD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| component | Yes | Name of the component to get documentation for |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
install-blocksD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| block | Yes | Name of the block to install | |
| runtime | No | User runtime (npm, pnpm, yarn, bun) |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
install-componentD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| component | Yes | Name of the component to install | |
| runtime | No | User runtime (npm, pnpm, yarn, bun) |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list-blocksD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list-componentsD
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
v1.0.0- First observed
get-block-docs - First observed
get-component-docs - First observed
install-blocks - First observed
install-component - First observed
list-blocks - First observed
list-components
TDQS
C2.1/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a clearly distinct purpose with no overlap: get-block-docs and get-component-docs retrieve documentation, install-blocks and install-component handle installation, and list-blocks and list-components provide listings. The block/component distinction and action types (get, install, list) create unambiguous boundaries.
Naming Consistency5/5
All tools follow a perfect verb-noun pattern with consistent kebab-case formatting: get-block-docs, get-component-docs, install-blocks, install-component, list-blocks, list-components. The naming is completely predictable and follows the same structural convention throughout.
Tool Count4/5
Six tools is reasonable for a Shadcn UI server, covering documentation retrieval, installation, and listing for both blocks and components. While slightly minimal, it provides core functionality without being overwhelming. A few additional tools like update or search might enhance it but aren't essential.
Completeness4/5
The toolset covers the main workflows for Shadcn UI: discovering components/blocks (list), accessing documentation (get), and installation (install). Minor gaps exist, such as no update/uninstall tools or search functionality, but the core CRUD-like operations for this domain are well-represented.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP server for building and testing AI agents with multi-model experimentation and insights.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn MCP server that enables AI assistants to search, discover, and install Aceternity UI components programmatically.575 npm25MIT
- AlicenseNot gradedqualityDmaintenanceThis MCP server provides tools to install and manage shadcn/ui components directly from AI coding agents.2MIT
- AlicenseAqualityCmaintenanceA secure MCP server that gives AI coding assistants direct access to the shadcn/ui registry, enabling fetching, installing, and wiring up components without switching context.822 npm4MIT