Lanhu MCP Server
The Lanhu MCP Server enables AI coding assistants (e.g., Cursor, Claude) to directly access and utilize Lanhu design and PRD content. It can:
Convert designs into pixel-perfect HTML/CSS with structured Design Tokens (colors, fonts, shadows, etc.).
Extract only design tokens for consistency checks, sorted by usage frequency.
Retrieve design slices, icons, and image assets automatically.
Analyze PRD or Axure prototypes from developer, tester, or explorer perspectives.
List all designs in a project or pages in a PRD/prototype.
Resolve Lanhu share/invite links into usable project URLs.
Allow fine-grained control over output content (HTML, images, tokens, layout, layers, slices) and layer depth.
Support parallel analysis of multiple designs with automatic retry on errors.
Provide built-in MCP prompt templates for frontend development and design review, plus resource URIs for project design lists.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Lanhu MCP Server Analyze this design link and generate the HTML and CSS code"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🎨 蓝湖 MCP Server
让 AI 编程助手直接读取蓝湖设计稿、提取代码、解析需求文档
这是什么
mcp-lanhu 是蓝湖的 MCP 服务器,装上之后 Cursor、Windsurf、Claude Desktop、Claude Code 都能直接连接蓝湖。AI 可以读取设计稿、提取 HTML/CSS、解析 PRD、下载切图,全程不用离开编辑器。
一行命令,零配置 —
npx -y mcp-lanhu,粘贴蓝湖链接就能用。
核心能力
设计稿 → 代码:生成像素级 HTML + CSS,含完整 Design Tokens(颜色、字体、阴影、渐变)
结构化 Design Tokens:提取所有颜色、字体族/字号/字重、阴影、边框、圆角,按使用频率排序
PRD 驱动开发:将 PRD 或 Axure 原型交给 AI,需求感知编码
自动切图:直接从蓝湖提取切图、图标和图片,无需手动导出
并发 + 重试:多设计稿并行分析,网络异常自动重试
MCP Resources & Prompts:内置前端开发和设计走查 Prompt 模板
Related MCP server: mcp-lanhu
安装
最快方式:让 AI 帮你装
复制下面这段话,发给你的 AI 助手(Cursor / Claude Code / Windsurf):
帮我安装蓝湖 MCP 服务器:https://github.com/MrDgbot/lanhu-mcp
AI 会自动读取仓库说明并完成配置,你只需要提供蓝湖 Cookie。
手动配置
无需 clone 代码,npx 自动安装。
Cursor / Windsurf — 编辑 .cursor/mcp.json(或 .windsurf/mcp.json):
{
"mcpServers": {
"lanhu": {
"command": "npx",
"args": ["-y", "mcp-lanhu"],
"env": { "LANHU_COOKIE": "your_cookie_here" }
}
}
}Claude Desktop — 编辑 claude_desktop_config.json:
{
"mcpServers": {
"lanhu": {
"command": "npx",
"args": ["-y", "mcp-lanhu"],
"env": { "LANHU_COOKIE": "your_cookie_here" }
}
}
}Claude Code:
claude mcp add lanhu -- npx -y mcp-lanhu然后设置环境变量 LANHU_COOKIE。
获取 Cookie
登录 蓝湖
F12 打开开发者工具 → Network 标签
复制任意请求的
Cookie请求头
配置完成后重启客户端,粘贴蓝湖链接即可使用。
工具
lanhu_design — 设计稿
通过 mode 参数切换功能:
Mode | 说明 |
| 列出项目所有设计图 |
| 设计图 → HTML+CSS + Design Tokens(默认) |
| 仅提取 Design Tokens(字体、颜色、阴影等) |
| 提取切图资源 |
analyze 模式支持 include 参数按需选择输出:html、image、tokens、layout、layers、slices。默认 ["html", "tokens", "layers", "image"]。请求 layers 时可用 layer_depth 控制嵌套深度:默认 4,0 仅返回顶层,"all" 返回完整图层树。每个设计会按请求项返回 success、partial_success 或 error,结构化图层标注位于 layer_annotations。
Design Tokens 输出示例:
=== Design Tokens ===
Colors (12 unique):
rgba(140,140,140,1) x48
rgba(255,255,255,1) x28
rgba(51,51,51,1) x12
...
Fonts (7 unique):
Source Han Sans CN / Regular / 14px x25
PingFang SC / Bold / 10px x3
...
Shadows (3 unique):
rgba(0,81,187,0.03) 0px 0px 0px 1px x3
...lanhu_page — PRD / 原型
Mode | 说明 |
| 列出 PRD 所有页面 |
| PRD/原型 → 结构化分析(默认) |
lanhu_resolve_invite — 解析邀请链接
将蓝湖分享链接解析为可用的项目 URL。
MCP Resources & Prompts
类型 | 名称 | 说明 |
Resource |
| 项目设计稿列表( |
Prompt |
| 根据设计稿生成像素级前端代码 |
Prompt |
| 审查设计一致性和可实现性 |
使用场景
前端开发:粘贴蓝湖链接 → AI 生成与设计稿匹配的组件代码
设计走查:对比实现与 Design Tokens(间距、颜色、字体)
需求实现:将 PRD 交给 AI,需求驱动的功能开发
资源导出:批量提取图标和图片
兼容性
客户端 | 支持 | 传输 |
Cursor | ✅ | stdio |
Windsurf | ✅ | stdio |
Claude Desktop | ✅ | stdio |
Claude Code | ✅ | stdio |
其他 MCP 兼容 IDE | ✅ | stdio |
开发
git clone https://github.com/MrDgbot/lanhu-mcp.git && cd lanhu-mcp
npm install && cp config.example.env .env # 填入 LANHU_COOKIE
npm run dev # 开发模式
npm run build # 构建
npm test # 测试FAQ
Q: 什么是 MCP? A: Model Context Protocol,让 AI 助手安全连接外部工具的开放标准。
Q: 支持哪些蓝湖套餐? A: 任何可网页访问的蓝湖账号,通过浏览器 Cookie 认证。
Q: analyze 返回太大怎么办?
A: 用 include 参数,如 ["tokens"] 只返回 Design Tokens;不需要 base64 图片时请不要包含 image。
Q: 不用 Cursor 也能用? A: 能。支持所有 MCP 客户端。
License
Available Tools
3 toolslanhu_designA
Unified Lanhu design tool. Supports listing, analyzing, extracting tokens, and getting slices.
Modes:
list: List all designs in the project
analyze: Full design analysis with HTML+CSS, tokens, layout (default)
slices: Extract slice/asset info for download
tokens: Extract design tokens only (fonts, colors, shadows, etc.)
For detailDetach URLs (contains image_id), pass design_names='all'.
Inputs: url (required), mode, design_names, include.
lanhu_pageB
Unified Lanhu PRD/prototype tool. Supports listing and analyzing pages.
Modes:
list: List all pages in a PRD/prototype document
analyze: Analyze specified pages (default)
Inputs: url (required), mode, page_names, analysis_mode.
lanhu_resolve_invite_linkB
Resolve Lanhu invite/share link to actual project URL with tid/pid/docId parameters.
Inputs: invite_url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
lanhu_design and lanhu_page both have 'list' and 'analyze' modes, which could cause confusion. Their names distinguish designs from pages, but the modes overlap. lanhu_resolve_invite_link is clearly distinct.
Two tools follow a noun-based pattern (lanhu_design, lanhu_page) while the third uses a verb phrase (lanhu_resolve_invite_link). The naming is mostly consistent but the third tool breaks the pattern.
3 tools is reasonable for a design collaboration server, covering design assets, pages, and link resolution. It could potentially be expanded, but it's not too few.
The server covers design listing/analysis, page listing/analysis, and link resolution. Missing are operations like creating or updating designs/pages, or managing slices directly. Core viewing and analysis are covered.
Maintenance
Related MCP Connectors
Prototypes made of HTML screens and the review notes designers dictate, ready for your AI to apply.
Deterministic Figma to Elementor, Gutenberg, Oxygen, Etch and HTML layouts for AI assistants.
Your AI agent designs editable, clickable UI prototypes on a live canvas.
UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI coding tools to read Lanhu design data and automate Design to Code, including project browsing, layer tree extraction, DDS semantic components, and code generation.1458 npm4MIT
- AlicenseAqualityCmaintenanceEnables AI coding assistants to directly access Lanhu design drafts, generate frontend code, parse PRDs, and download design assets.3301 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to read Lanhu design collaboration content: extracting and analyzing Axure prototype pages, downloading UI designs and slices, and converting design specs into HTML+CSS for implementation. It also provides a shared team message board so multiple AI tools can reuse requirement analyses and knowledge across projects.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to read Lanhu design specs — layer trees with per-layer CSS, screenshots, downloadable slices, and review comments — so they can restore UI and generate React/Vue/mini-program code without manual measuring or asset hunting.MIT