What is uml-mcp-llm-visualizer?

A diagram tool for showing neural networks and large language model architectures in two or three dimensions. A large language model is an AI model that generates and understands text; a neural network is a layered model used for tasks such as prediction and generation.

Use it to draw transformers, autoencoders, variational autoencoders, or GANs as a 2D map or a rotatable 3D scene.

It helps people inspect the structure and repeated layers of an AI model more easily than source code or a written list.

How antoinebou12/uml-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to antoinebou12/uml-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/antoinebou12/uml-mcp/main/.github/skills/uml-mcp-llm-visualizer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/antoinebou12/uml-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer/github.svg)](https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer)

Your own site

<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-llm-visualizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,197 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01197
Opus 5.5	$0.00015	$0.00479
Sonnet 5.5	$0.00008	$0.00239
Haiku 4.5	$0.00004	$0.00120

Measured today against content hash 2f57f04e38ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uml-mcp-llm-visualizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/uml-mcp-llm-visualizer/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM visualizer

Follow skill://uml-mcp-diagrams/SKILL.md. Layer maps, autoencoder and GAN shapes, grouped N× blocks, and a rotatable 3D scene from one JSON source.

Types

Type	Use for	Example prompt
`llm_2d`	a neural network or LLM architecture as a 2D map, or an autoencoder, VAE or GAN	Draw a VAE: input image, encoder, 2D latent z, decoder, reconstruction.
`llm_3d`	the same model as a rotatable 3D scene: layer panels, with encoder and decoder funnels	Show the VAE as a 3D scene I can rotate, encoder narrowing to the latent and decoder widening back.

Steps

Check the live catalog (list_diagram_types or uml://types); the bundled plugins are on by default, but a server may turn them off with plugins.bundled: false.
Read the type's example from uml://examples and keep its field names.
Call validate_uml; an error names the field and, for a bad reference, lists the known ids, so fix it and validate again.
Render with generate_uml_image for a chat image, or generate_uml with output_format: "html" for the interactive page in the MCP App viewer. Clients without MCP Apps still get the PNG and SVG.
Pass theme (auto, dark, light) rather than editing colours.

Recipes

Model	Layers (`kind`)
Autoencoder	`input` → `encoder` → `bottleneck` → `decoder` → `output`
VAE	`input` → `encoder` → two `vector` heads (μ, log σ²) → `bottleneck` (z = μ + σ ⊙ ε) → `decoder` → `output`
GAN	`token` (noise) → `decoder` (generator) → `vector` (fake sample) → `decision` (discriminator); a `dashed` edge for real data
Decoder-only LLM	`input` → `embedding` → `attention` and `feedforward` (`repeat: 32`) → `normalization` → `output`; a `dashed` residual edge
Encoder-decoder transformer	two `groups` with `repeat: 6`: `encoder` and `decoder` layers inside, a cross-attention edge between them

Use label and kind. The parser also accepts name and type and infers a missing kind from the id and label (encoder, decoder, latent, input, output...), but explicit kinds give the shapes you expect. Give a title (the default is "Model architecture").

Read the full file on GitHub · 46 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +16 lines 2f57f04e38ad
yesterday First seen · 30 lines · 38 tokens per session scan A a7f99a498cb9

Subscribe to this mod's changes

uml-mcp-llm-visualizer is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,197 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.

Data and AI Design and UX mcp uml

uml-mcp-llm-visualizer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
uml-mcp-llm-visualizerantoinebou12/uml-mcp	Skill	109	yesterday	MIT	A	38	Claude Code, Codex
planjeremylongshore/tons-of-skills-marketplace	Skill	2.9k	yesterday	MIT	A	144	Claude Code
dstack-prototypingdstackai/dstack	Skill	2.3k	yesterday	MPL-2.0	A	80	Claude Code, Codex
senior-data-engineerbenchflow-ai/skillsbench	Skill	1.9k	2d ago	Apache-2.0	A	100	Claude Code, Codex
llm-icon-finderdaymade/claude-code-skills	Skill	1.5k	yesterday	MIT	A	61	Claude Code, Codex
enhance-promptgoogle-labs-code/stitch-skills	Skill	8.7k	2mo ago	Apache-2.0	A	41	Claude Code
bim-classification-aidatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction	Skill	394	18d ago	MIT	A	35	Claude Code, Codex

uml-mcp: Skill for Claude Code