What is uml-mcp-diagrams?

A diagram-making tool that turns text written in formats such as PlantUML, Mermaid, or D2 into diagrams and shareable Kroki links. It can also check whether diagram text is valid.

Use it to create, validate, and share software diagrams such as system designs, flowcharts, and UML diagrams.

It removes the need to manually render diagrams or guess whether their source text will work.

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-diagrams/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-diagrams/github.svg)](https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-diagrams)

Your own site

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

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,322 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Agent Snooping · line 10
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

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	$0.00023	$0.01322
Opus 5.5	$0.00009	$0.00529
Sonnet 5.5	$0.00005	$0.00264
Haiku 4.5	$0.00002	$0.00132

Measured yesterday against content hash 9a8784017e4e, 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-diagrams 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 yesterday.

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-diagrams/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagram workflow

Use the server's current catalog before choosing a renderer. Read uml://types and uml://formats, or call list_diagram_types. Installed plugins extend the catalog: never conclude D3 is unsupported from a remembered list. If D3 types are present, render with those types through the normal generation tools. If absent, explain that this server has not enabled the plugin.

Choose a focused workflow

Read the relevant guide through resources/read when needed:

Request	Resource	Local skill
D3, cloud logos, custom plugins	`skill://uml-mcp-guides/d3-plugins/SKILL.md`	`.skill/skills/uml-mcp-d3-plugins/SKILL.md`
Stack and cloud diagrams with logos	`skill://uml-mcp-guides/stack-diagram/SKILL.md`	`.skill/skills/uml-mcp-stack-diagram/SKILL.md`
Archify architecture, workflow, sequence	`skill://uml-mcp-guides/archify/SKILL.md`	`.skill/skills/uml-mcp-archify/SKILL.md`
LLM and neural-network diagrams, 2D and 3D	`skill://uml-mcp-guides/llm-visualizer/SKILL.md`	`.skill/skills/uml-mcp-llm-visualizer/SKILL.md`
Complex Mermaid	`skill://uml-mcp-guides/mermaid/SKILL.md`	`.skill/skills/uml-mcp-mermaid/SKILL.md`
PlantUML and C4 levels	`skill://uml-mcp-guides/plantuml-c4/SKILL.md`	`.skill/skills/uml-mcp-plantuml-c4/SKILL.md`
Several views or format conversions	`skill://uml-mcp-guides/batch/SKILL.md`	`.skill/skills/uml-mcp-batch/SKILL.md`

MCP skills/list exposes this entry point. The seven focused skills are available on demand through the resource template and the agent-skills index. For other notations, read uml://templates, uml://examples, or the per-type local skill at .skill/skills/<diagram_type>/SKILL.md.

Generate and verify

Record the components and directed, labelled relationships from the request. Preserve their identity across D3, D2, Mermaid and C4 conversions. C4 levels change scope deliberately; explain what each level expands.
Choose a catalog type matching the source language. Use the configured Kroki endpoint first for Kroki types. Naming Mermaid or PlantUML selects notation; a different service requires an explicit request or a documented fallback.
Use validate_uml for unfamiliar or complex source. Mermaid sequences need one statement per line; use strict: true when appropriate. Validation alone does not prove that an image was rendered or its text is readable.
Call generate_uml_image for a visible preview, generate_uml for a link, or generate_uml_batch for several views. Request output_format: svg in MCP Apps whenever the catalog supports it. Plain image clients usually need PNG; the server can rasterize SVG-only formats. Leave output_dir unset unless the user asks to write server-side files.
Check error, success, mime_type, returned bytes and render attempts. Verify the visible preview, labels and links when the host permits inspection. A render URL or valid: true is not evidence that the client displayed it. Report unverified display or inaccessible links plainly; never invent URLs.

Read the full file on GitHub · 93 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.

yesterday Changed · +3 lines 9a8784017e4e
5d ago Changed · -86 lines · -25 tokens per session bf423469c1b5
8d ago Changed ff48567b4473
13d ago Changed · +16 lines · -35 tokens per session bd37dab9fd94
1mo ago Changed 43a4455c3405
2mo ago Changed · +44 lines · +14 tokens per session 12e5085387f5
2mo ago First seen · 116 lines · 69 tokens per session scan A be872759dbb8

Subscribe to this mod's changes

uml-mcp-diagrams is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 1,322 once invoked, about $0.0001 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 2026-08-30.

Design and UX mcp uml

uml-mcp-diagrams next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
uml-mcp-diagramsantoinebou12/uml-mcp	Skill	109	yesterday	MIT	A	23	Claude Code, Codex
detailed-designpan94u/forge	Skill	40	5d ago	none	A	27	Claude Code
architecture-diagram-creatorbookforge-ai/bookforge-skills	Skill	42	6mo ago	CC-BY-SA-4.0	A	128	Claude Code
webgl-holographic-foilnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	41	Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	53	Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-design	Skill	106k	yesterday	Apache-2.0	A	78	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	3d ago	MIT	A	52	Codex

uml-mcp: Skill for Claude Code