String Diagram Generator MCP Server
Generates formal string diagram visualizations of Lushy brick compositions, enabling zero-cost diagram generation and recursive self-documentation based on category theory.
README
String Diagram Generator MCP Server
Category-theoretic visualization of Lushy brick compositions
Overview
The String Diagram Generator is a meta-brick MCP server that generates formal string diagram visualizations of Lushy workflow compositions. It demonstrates category theory foundations through recursive self-documentation capability.
Key Features
- 🎨 Zero-cost diagram generation (0 tokens in deterministic mode)
- 🔄 Recursive capability (can diagram itself!)
- 📊 Cost analysis (visualize token usage across layers)
- ✅ Validation (catch composition errors before generation)
- 🎯 Production-ready (full test suite, comprehensive docs)
Category Theory Foundation
Graded Traced Symmetric Monoidal Category over Kleisli(LLM)
- Traced: Feedback loops for versioning and validation
- Graded: Cost tracking (Grade 0 = free, Grade 1 = LLM, Grade 2 = human)
- Symmetric Monoidal: Sequential (∘) and parallel (⊗) composition
- Over Kleisli(LLM): Probabilistic composition with reproducibility bounds
Quick Start
Installation
# Clone repository
git clone https://github.com/lushy/string-diagram-mcp.git
cd string-diagram-mcp
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests
./tests/run_tests.sh
Usage as MCP Server
# Run locally
python src/string_diagram_mcp/server.py
# Or configure in Claude Desktop
# Add to claude_desktop_config.json:
{
"mcpServers": {
"string-diagram-generator": {
"command": "python",
"args": ["/path/to/string-diagram-mcp/src/string_diagram_mcp/server.py"]
}
}
}
MCP Tools
1. generate_string_diagram
Generate a string diagram from brick composition (0 tokens)
2. generate_meta_diagram
Generate diagram of the generator itself (0 tokens)
3. get_brick_layer_info
Get four-layer architecture details (0 tokens)
4. create_sample_diagram
Generate sample diagrams for demos (0 tokens)
5. validate_composition
Validate brick compositions (0 tokens)
6. get_server_info
Get server metadata (0 tokens)
Architecture
Four-Layer Structure
┌─────────────────────────────────┐
│ Layer 4: Contextual (Grade 0/1)│ SVG rendering + cost analysis
├─────────────────────────────────┤
│ Layer 3: Relational (Grade 0) │ Wire routing & crossing detection
├─────────────────────────────────┤
│ Layer 2: Structure (Grade 0) │ Topological layout computation
├─────────────────────────────────┤
│ Layer 1: Foundation (Grade 0) │ Primitives & validation
└─────────────────────────────────┘
Documentation
- User Guide - Complete usage documentation
- API Reference - Tool specifications
- Architecture - Technical deep-dive
- Examples - Sample workflows and outputs
Development
# Run tests with coverage
pytest --cov=string_diagram_mcp
# Format code
black src/ tests/
# Lint
ruff check src/ tests/
# Type check (if you add type hints)
mypy src/
Cost Analysis
Typical Workflow Savings:
- 3-brick workflow: 75% savings (450 vs 1800 tokens)
- 5-brick workflow: 80% savings (800 vs 4000 tokens)
String Diagram Generator itself:
- Deterministic mode: 0 tokens
- With LLM annotations: ~200 tokens
License
MIT License - see LICENSE file
Contributing
Contributions welcome! Please see CONTRIBUTING.md
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Email: support@lushy.ai
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。