# Penrose

> Use this tool when you need to generate accurate and visually appealing mathematical diagrams using natural language inputs. It solves problems in mathematical communication, particularly in educational contexts, research papers, and technical presentations, by bridging the gap between natural language and Penrose's domain-specific languages. The tool takes natural language inputs and outputs mathematical diagrams, making it easier for AI models to create complex diagrams without requiring deep knowledge of underlying systems.

Canonical page: https://skillsregistry.net/skills/teglon-labs-penrose  
JSON: https://api.skillsregistry.net/v1/skills/teglon-labs-penrose

## Description

This Penrose MCP server, developed by Teglon Labs, provides a TypeScript-based interface for AI assistants to create mathematical diagrams using Penrose's domain-specific languages. Built with the Model Context Protocol SDK, it offers tools for defining mathematical types, describing objects and relationships, and specifying visual representation rules. The implementation focuses on bridging natural language inputs with Penrose's DSL, Substance, and Style languages, making it easier for AI models to generate accurate and visually appealing mathematical diagrams. It's particularly useful for enhancing mathematical communication in educational contexts, research papers, or technical presentations, enabling the creation of complex diagrams without requiring deep knowledge of Penrose's underlying systems.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/teglon-labs-penrose)
- **Repository:** <https://github.com/bmorphism/penrose-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "teglon-labs-penrose"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/teglon-labs-penrose` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/teglon-labs-penrose/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt