axure-mcp-server
Extracts text, image links, and structural content from public Axure share pages to enable AI-powered prototype summarization. It features multi-page crawling and OCR fallback to process image-only designs for downstream LLM analysis.
README
axure-mcp-server
MCP server for extracting visible text and image links from public Axure share pages, so AI tools (Cursor/Claude Desktop/others with MCP support) can summarize prototype content.
Features
- Extract visible text blocks from Axure page DOM
- Extract image URLs (optionally image base64 payload)
- Auto-discover and crawl additional same-origin Axure pages
- OCR fallback when text is image-only or too little
- Return structured JSON for downstream AI summarization
- Build an AI-ready summary prompt in one call
- Works with MCP clients via stdio
Requirements
- Node.js >= 18
- npm >= 9
If your local Node is old (for example Node 16), upgrade first:
# if you use nvm
nvm install 20
nvm use 20
node -v
Quick Start
npm install
npx playwright install chromium
npm run build
npm start
MCP Tools
1) axure_health
Health check of runtime.
2) axure_fetch
Input:
{
"url": "https://vscn2w.axshare.com/?id=xpnh6e&p=%E5%8E%9F%E5%9E%8B%E6%96%B9%E6%A1%88&sc=3",
"timeoutMs": 45000,
"maxImages": 30,
"maxTexts": 300,
"crawlPages": true,
"maxPages": 5,
"enableOcrFallback": true,
"ocrMinTextCount": 8,
"ocrMaxImages": 3,
"ocrLanguage": "chi_sim+eng",
"includeImageBase64": false
}
Output: JSON with status, textBlocks, imageItems, pages, warnings, stats (including ocrTextCount).
3) axure_summary_prompt
Input:
{
"url": "https://vscn2w.axshare.com/?id=xpnh6e&p=%E5%8E%9F%E5%9E%8B%E6%96%B9%E6%A1%88&sc=3",
"focus": "请提炼核心流程和页面功能点",
"crawlPages": true,
"maxPages": 6,
"enableOcrFallback": true
}
Output: an AI-ready plain text prompt including extracted texts and image links.
Use in Cursor
Add to MCP config (example):
{
"mcpServers": {
"axure-mcp": {
"command": "node",
"args": ["/ABSOLUTE/PATH/axure-mcp-server/dist/index.js"]
}
}
}
If published to npm:
{
"mcpServers": {
"axure-mcp": {
"command": "npx",
"args": ["-y", "axure-mcp-server"]
}
}
}
Compatibility: keep Node 16 globally, run MCP on Node 20
If your main frontend stack (for example Vue2) must stay on Node 16, you can still run this MCP safely by pinning only this server to Node 20 in Cursor:
{
"mcpServers": {
"axure-mcp": {
"command": "npx",
"args": [
"-y",
"node@20",
"/Users/55haitao/Desktop/axure-mcp-server/dist/index.js"
]
}
}
}
This keeps your global Node unchanged while ensuring axure-mcp-server runs with a compatible runtime.
Compatibility after npm publish
If you publish this package to npm, and still need to keep global Node 16, use Node 20 only for this MCP process:
{
"mcpServers": {
"axure-mcp": {
"command": "npx",
"args": [
"-y",
"node@20",
"/usr/local/bin/npx",
"-y",
"axure-mcp-server"
]
}
}
}
If your system npx path is different, replace "/usr/local/bin/npx" with your actual path from which npx.
Publish to GitHub
git init
git add .
git commit -m "feat: init axure mcp server"
git branch -M main
git remote add origin <your-repo-url>
git push -u origin main
Publish to npm
Before publish:
- Update
package.jsonfields (name,author,repository,homepage) - Ensure build output exists:
npm run build
Then:
npm login
npm publish --access public
Roadmap
- Add optional multi-page navigation and auto-click flow
- Export markdown report and downloadable screenshot package
Notes
- Designed for public/no-login Axure links.
- Respect source site terms and data usage permissions.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。