Skip to main content
Glama
design-inspiration

design-inspiration

by SankofaForge

design-inspiration

一个搜索 Dribbble、Behance、Awwwards、Mobbin 和 Pinterest 以获取 UI 设计灵感的 MCP 服务器。专为 Claude Code 构建,但可与任何 MCP 客户端配合使用。

使用 Serper API(Google 搜索)并附加 site: 过滤器,将结果限定在特定设计平台内。还可以通过无头浏览器从任何实时网站提取实际的设计令牌(颜色、字体、间距)。

找到灵感,然后从你喜欢的网站提取精确的令牌。

为什么

我希望 Claude 在构建 UI 时能拉取设计参考——查看真实的 Dribbble 作品、寻找配色方案、浏览布局模式——而无需离开终端。现有的方案要么需要 Playwright(过于笨重),要么无法返回我可以实际下载和查看的图片 URL。

搜索部分封装了 Serper 的图片和网页搜索端点,并预配置了站点过滤器。就这么简单。

令牌提取部分则源于另一个痛点:我在 Dribbble 上找到一个喜欢的网站,打开它,然后手动用取色器取色并检查字体。现在只需将 design_extract_tokens 指向该 URL,就能直接获得精确的值。

Related MCP server: DOM Inspector Plus MCP Server

工具

design_search_images — 跨设计平台的图片搜索。返回图片 URL、尺寸、来源链接。适合查找特定 UI 模式的视觉参考。

design_search_references — 限定在设计类网站内的网页搜索。返回文章标题、摘要、链接。更适合查找案例研究、设计系统文档或模式说明。

design_search_styles — 搜索特定的美学方向(配色方案、排版、布局、动画)。并行运行图片和网页搜索,返回合并结果。

design_extract_tokens — 从实时网站提取设计令牌。指向任意 URL 即可获得颜色、排版、间距、圆角和阴影。支持 dark_mode 和 mobile 标志。需要全局安装 dembrandt(npm install -g dembrandt)。

三个搜索工具均接受 sites 参数以过滤到特定平台,以及 num 参数以控制结果数量。

设置

搜索工具需要 Serper API 密钥。免费层提供 2,500 次搜索,无需信用卡。

  1. 在 serper.dev 注册

  2. 复制你的 API 密钥

对于令牌提取,请全局安装 dembrandt:

npm install -g dembrandt

Claude Code

claude mcp add design-inspiration -e SERPER_API_KEY=your-key-here -- node /path/to/design-inspiration-mcp-server/dist/index.js

任何 MCP 客户端(stdio)

{
  "design-inspiration": {
    "type": "stdio",
    "command": "node",
    "args": ["/path/to/design-inspiration-mcp-server/dist/index.js"],
    "env": {
      "SERPER_API_KEY": "your-key-here"
    }
  }
}

从源码构建

git clone https://github.com/YonasValentin/design-inspiration-mcp-server.git
cd design-inspiration-mcp-server
npm install
npm run build

实际工作原理

每个工具通过在你搜索的内容后附加 site:dribbble.com OR site:behance.net OR ... 来构建搜索查询。然后调用 Serper 的 /images 或 /search 端点并格式化响应。

design_search_styles 工具并行运行两个端点(Promise.all),以获取同一查询的图片和文章。

design_extract_tokens 通过 child_process.execFile 调用 dembrandt(使用 --json-only),解析 JSON 输出,并将其格式化为 markdown 和结构化数据。60 秒超时。无额外 npm 依赖——dembrandt 作为全局 CLI 运行,child_process 是内置的。

结果同时以 markdown(用于显示)和结构化 JSON(用于程序化使用)返回。响应在 25,000 个字符处截断,以避免淹没上下文窗口。

使用技巧

搜索具体的 UI 模式,而不是泛泛的术语:

# good
"fintech dashboard dark mode"
"mobile onboarding flow card swipe"
"saas pricing page comparison table"

# too vague
"nice website"
"good design"

你可以下载返回的图片 URL,并让 Claude 直接查看:

curl -sL "https://cdn.dribbble.com/..." -o /tmp/reference.jpg

然后让 Claude 读取图片文件——它可以看到并描述设计。

许可证

MIT

声明式 3D 资产工作流

引用可以声明某个网站概念需要 3D 资产。design_prepare_references 验证该需求并返回 assetPlan;它不会创建文件、调用 Blender 或调用其他 MCP。

当资产计划包含 route: "blender" 时,宿主应用程序或代理必须将该任务路由到可用的 Blender MCP。这是宿主级别的路由,不是本服务器执行的调用。在 Blender 任务中保留资产 ID 和验收要求。

使用 examples/blender-asset-task.json 作为交接格式。包括主题、视觉意图、相机、构图、材质、光照、动画、面向 Web 的输出格式、性能限制和验收预期。Web 输出通常包括压缩的 .glb 或 .gltf 以及 .png 或 .webp 回退。验收验证干净的查看器加载、构图、材质、动画和性能预算。

预期交接:design_prepare_references -> assetPlan.route = "blender" -> 宿主应用 -> Blender MCP -> 原生站点实现和浏览器 QA。

未经用户批准,不得用 CSS 或占位符替换声明的 3D 需求。如果 Blender 不可用,请报告受阻的资产任务并保留声明式交接。

Available Tools

5 tools
design_extract_tokensExtract design tokens from websiteA
Read-onlyIdempotent

Extract actual design tokens (colors, typography, spacing, borders, shadows) from a live website using headless browser. Give it any URL and get back the exact values used. Pairs well with the search tools — find inspiration, then extract tokens from sites you like.

NameRequiredDescriptionDefault
urlYesWebsite URL to extract design tokens from. Examples: "https://stripe.com", "https://linear.app"
mobileNoExtract from mobile viewport (375px)
dark_modeNoExtract colors from dark mode variant
design_prepare_referencesPrepare design referencesA
Read-onlyIdempotent

Validate and normalize selected references. Does not browse, capture, or invoke other MCPs.

NameRequiredDescriptionDefault

No parameters

design_search_imagesSearch design imagesA
Read-onlyIdempotent

Image search across Dribbble, Behance, Awwwards, Mobbin, and Pinterest. Returns image URLs, dimensions, and source links. Use specific UI terms ("fintech dashboard dark mode") over vague ones ("nice design").

NameRequiredDescriptionDefault
numNoNumber of image results to return (1-40, default: 10)
queryYesUI design search query. Examples: "dashboard dark mode", "mobile onboarding flow", "saas pricing page"
sitesNoFilter to specific design sites. Empty array searches all sites. Options: dribbble, behance, awwwards, mobbin, pinterest
design_search_referencesSearch design referencesA
Read-onlyIdempotent

Web search scoped to design platforms. Returns article titles, snippets, and links. Better than image search when you want case studies, write-ups, or design system documentation.

NameRequiredDescriptionDefault
numNoNumber of results to return (1-20, default: 10)
queryYesUI design search query. Examples: "best dashboard designs 2025", "mobile navigation patterns"
sitesNoFilter to specific design sites. Empty array searches all sites.
design_search_stylesSearch design stylesA
Read-onlyIdempotent

Search for a specific aesthetic direction — color palettes, typography, layouts, or animation references. Runs image and web search in parallel and returns combined results.

NameRequiredDescriptionDefault
numNoNumber of results (1-20, default: 10)
typeNoType of style inspiration to search forgeneral
styleYesDesign style to search for. Examples: "minimalist dark theme", "brutalist web design", "glassmorphism"

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 5 tool updatesv1.0.0
    • First observeddesign_extract_tokens
    • First observeddesign_prepare_references
    • First observeddesign_search_images
    • First observeddesign_search_references
    • First observeddesign_search_styles

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation4/5

The tools are largely distinct: search_images handles image lookup, search_references handles textual content, extract_tokens handles live site analysis, and prepare_references handles validation. However, design_search_styles blends image and web search for style-specific queries, which overlaps with the first two but is differentiated by its focus on aesthetic direction like color palettes and typography.

Naming Consistency5/5

All tools follow a consistent design_<verb>_<noun> pattern with snake_case and clear verbs (search, extract, prepare). No variation in casing or verb style, making the naming predictable and easy to navigate.

Tool Count5/5

With 5 tools, the server is well-scoped for a design inspiration use case. Each tool serves a distinct purpose—searching visuals, text, styles, extracting tokens, and preparing references—without unnecessary bloat or minimal coverage.

Completeness4/5

The surface covers the core workflow: search for inspiration (images, references, styles), extract tokens from a chosen site, and prepare references for use. Minor gaps exist, such as no explicit tool to fetch or save a specific reference beyond token extraction, but the primary use cases are well covered.

Maintenance

ActivityActive
ResponsivenessNo recent community issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    C
    maintenance
    Analyzes and extracts design tokens, assets, and layout from live websites to enable AI clients to faithfully replicate them, with tools for screenshotting, component inspection, and pixel-diff verification.
    14
    29 npm
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables assistants to discover, search, and extract real design systems — palettes, type scales, spacing, surfaces, and do/don't guidance — from the public style pages of styles.refero.design. It reports index coverage with every search and renders matched styles as structured design.md sections or parsed JSON tokens.
    6
    27 npm
    1
    MIT