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
- šØ Zero-cost diagram generation (0 tokens in deterministic mode)
- š Recursive capability (can diagram itself!)
- š Cost analysis (visualize token usage across layers)
- ā Validation (catch composition errors before generation)
- šÆ 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 (ā) and parallel (ā) 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
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Layer 4: Contextual (Grade 0/1)ā SVG rendering + cost analysis
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Layer 3: Relational (Grade 0) ā Wire routing & crossing detection
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Layer 2: Structure (Grade 0) ā Topological layout computation
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¤
ā Layer 1: Foundation (Grade 0) ā Primitives & validation
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.