AI Diagram Prototype Generator
An AI-powered diagram and prototype generator MCP server built by SimonUTD that integrates with multiple AI providers (ZhipuAI, OpenAI, Gemini) to automatically generate architecture diagrams, flowcharts, and mobile app prototypes. Features specialized prompt templates for different diagram types including system architecture, Apple mobile prototypes, WeChat mini-apps, and common UI prototypes, with configurable AI model selection and token limits. Designed for developers, architects, and designers who need rapid visual prototyping and diagram generation capabilities integrated into their workflow.
I/O
heuristic · beta该 skill 无 npm 包，暂用描述启发式推断 I/O；接入后可实测。
综合分
效果测评卡
进行中 · 待运行真实 I/O 已解决「输入输出是什么」；下一步接 agent 真跑，量化「效果好不好」。
@antv/mcp-server-chart is a TypeScript-based server that enables AI assistants to generate data visualizations using AntV's charting capabilities. Developed by the AntV Visualization Team, it implements the Model Context Protocol to provide a standardized interface for creating various chart types from data. The server exposes chart generation functionality that can be accessed through MCP tools, making it particularly valuable for applications that need to produce visual data representations through conversational interfaces without requiring direct knowledge of visualization libraries.
Provides AI assistants with on-demand access to 141 documentation pages, 283 code examples, and 1,098 class API references for amCharts 5. Instead of loading the entire reference into context, the server lets AI query exactly what it needs — specific chart type references, code examples, or API lookups. Supports searching docs, browsing examples by category, and retrieving quick-start templates for any chart type.
CAFE provides AI agents with access to Dangamsoft's classical East Asian knowledge engine for Korean Saju (Four Pillars of Destiny) analysis. Five tools cover full Saju chart generation from birth date and time, five-element (Ohaeng) balance scoring, Gyeokguk pattern classification, Yin-Yang Johu harmony assessment, and Yongshin candidate determination. The underlying engine combines classical theory with machine learning, achieving 91.1% accuracy on five-class Yongshin classification.