lanhu-mcp
MCP server that integrates AI coding assistants with Lanhu (a design collaboration platform), enabling automated requirement analysis from Axure prototypes, UI design extraction with HTML/CSS code generation, and team collaboration via shared message board.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Cookie-based auth with manual extraction is fragile and insecure. Cookies stored in .env file. Browser automation (Playwright) adds attack surface. Task-type messages have safety restrictions preventing code mods/deletions. No TLS enforcement documented for local server.
⚡ Reliability
Best When
Your team uses Lanhu for design handoff and you want AI coding assistants to automatically extract requirements and generate code from designs.
Avoid When
You don't use Lanhu, or your AI model lacks vision capabilities. Also avoid if you need to modify designs programmatically.
Use Cases
- • Automatically analyzing Axure prototypes and extracting developer requirements with >95% claimed accuracy
- • Downloading design mockups and converting design parameters to HTML+CSS code
- • Sharing knowledge and task coordination across AI assistants via team collaboration board
- • Integrating design workflow with AI coding tools like Cursor, Windsurf, and Claude Code
Not For
- • Teams not using Lanhu as their design platform
- • Text-only AI models without vision capabilities (requires Claude, GPT-4, Gemini, etc.)
- • Workflows requiring design modification (read-only design access)
Interface
Authentication
Uses browser cookie-based authentication against Lanhu's web API. Cookies must be manually extracted from browser DevTools and configured. Cookies expire and require re-authentication.
Pricing
The MCP server is free. Lanhu platform may have its own pricing.
Agent Metadata
Known Gotchas
- ⚠ Requires vision-capable AI models (GPT-4, Claude, Gemini); text-only models will fail
- ⚠ Cookie-based auth expires and requires manual re-extraction from browser DevTools
- ⚠ Unofficial third-party project — not affiliated with Lanhu company
- ⚠ Task-type messages restrict AI to read-only operations for safety
- ⚠ Requires Playwright/Chromium installation for screenshot capabilities
- ⚠ Documentation is primarily in Chinese
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for lanhu-mcp.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-08.