stoners-design

stoners-design

MCP server providing 51 design skills covering product thinking, UX, visual design, Figma, frontend, motion, branding, and portfolio storytelling, accessible via tools and resources.

Category
访问服务器

README

Stoner's Design

Stoner's Design

51 design skills. One portable collection for product thinking, UX, visual design, Figma, frontend craft, motion, branding, and portfolio storytelling.

The repository combines the open SKILL.md format with native manifests for Codex, Claude Code, Gemini CLI, GitHub Copilot CLI, and compatible Cursor workflows. It also includes a dependency-free MCP server for clients that support Streamable HTTP or stdio.

What it can do

  • Shape product strategy, flows, edge cases, audits, and handoff
  • Design or critique UI with stronger hierarchy, typography, spacing, interaction, and accessibility
  • Work through Figma implementation and design-system tasks
  • Build distinctive frontend experiences and translate images into code
  • Create brand systems, logos, high-end visual direction, and motion
  • Structure portfolio stories and product-design case studies

Install

Codex

codex plugin marketplace add studioinfj-art/stoners-design
codex plugin install stoners-design@stoners-design-marketplace

Claude Code

claude plugin marketplace add studioinfj-art/stoners-design
claude plugin install stoners-design@stoners-design-marketplace

Gemini CLI

gemini extensions install https://github.com/studioinfj-art/stoners-design

GitHub Copilot CLI

copilot plugin install studioinfj-art/stoners-design

Cursor and other Agent Skills clients

Use the repository's skills/ directory as a skill source, or install individual skills into the client's supported skills directory. Cursor recognizes the same SKILL.md structure.

Any MCP client

Use the hosted Streamable HTTP endpoint:

https://stoners-design-mcp.vercel.app/mcp

Codex:

codex mcp add stoners-design --url https://stoners-design-mcp.vercel.app/mcp

Claude Code:

claude mcp add --transport http stoners-design https://stoners-design-mcp.vercel.app/mcp

For other clients, choose the Streamable HTTP transport and paste the same endpoint.

To run the MCP locally instead, clone the repository and configure this stdio server:

{
  "mcpServers": {
    "stoners-design": {
      "command": "node",
      "args": ["/absolute/path/to/stoners-design/mcp/server.mjs"]
    }
  }
}

The MCP exposes list_design_skills, search_design_skills, get_design_skill, and get_design_skill_file, plus one readable resource per skill.

Requirements

  • Node.js 18 or later for MCP
  • The host AI tool's current plugin, extension, Agent Skills, or MCP support
  • Any tool-specific dependencies named by an individual skill, such as Figma access or a frontend runtime

Licensing

The original MCP server, manifests, packaging, and documentation are MIT licensed. Individual skills and bundled resources retain their own upstream terms. Review THIRD_PARTY_NOTICES.md before redistributing or modifying the collection.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选