claudeers.
// MCP Servers

sketchy

A layout engine for LLM diagrams: Claude says what to draw, Sketchy figures out where. Hand-drawn, interactive, no overlapping boxes.

// MCP Servers[ cli ][ api ][ desktop ][ web ][ mobile ][ claude ]#claude#claude-code#claude-skill#claude-skills#diagrams#elkjs#layout-engine#mcp#mcp-servers◷ MIT$open-sourceupdated 18 days ago
Actively maintained
100/100
last commit 8 days ago
last release 9 days ago
releases 8
open issues 4

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up sketchy (npm project) into my current project.
Found on https://claudeers.com/sketchy
Repo: https://github.com/ddkbs/sketchy
Homepage/docs: https://sketchy.davidkubus.dev
Detected install method: npm → npm install @ddkbs/sketchy
Category: mcp-servers. Platforms: cli, api, desktop, web, mobile.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
active; community-verified: false. Confirm the source before running anything.
// or install directly (npm)
npm install @ddkbs/sketchy
// or clone
git clone https://github.com/ddkbs/sketchy

// compatibility

Platformscli, api, desktop, web, mobile
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageTypeScript

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

Sketchy

Sketchy lets Claude draw while it explains: clean, hand-drawn, interactive diagrams rendered right next to the answer. It works in the Claude chat as a skill and in Claude Code as an MCP server.

Claude decides what to draw and label. Sketchy decides where: a part library with named anchor points and automatic layout. Claude never computes coordinates, so drawings come out precise and consistent every time.

An interactive Sketchy drawing inside a Claude Code chat: what happens when you open a web page

What it can draw

Systems, step by step

Ask "What happens when I open a web page?" and Claude draws the whole path, then walks you through it. Each step circles what matters in red pen and fades the rest. Use the buttons or the arrow keys.

The life of a web request, from the browser through CDN, load balancer and services to cache, database and queue

Step 5 of the walkthrough: the orders service, cache and database are circled

Concepts from computer science and machine learning

Sketchy is not limited to hardware. Structure, flow, comparison and metaphor patterns cover any topic, from transformers to TCP.

How an LLM picks the next word: tokenizer, embeddings, a transformer block with self-attention and MLP, and sampling

Your own code

Ask "Explain my repo". Claude reads the code and draws modules, folders and data flow. Click a box to open the file in VS Code, Cursor, Windsurf or Zed; hover to see what it does.

Architecture of a repository with nested folders

Circuits from Arduino and ESP32 sketches

Ask "How is my sketch wired?". Claude reads pinMode, digitalWrite and friends, places real parts (50 boards, sensors, displays and modules from wokwi-elements) and connects pins by name. Sketchy routes the wires and places the callouts.

ESP32 with PIR sensor, DHT22, buzzer and status LEDArduino Uno driving an LED through a resistor

Labeled photos

Claude finds a freely licensed photo (Wikimedia Commons, Openverse), and a vision model running on your computer (Florence-2) locates the parts and printed text to label. Attribution is always shown.

Photo of an Arduino Uno with labeled parts

Comparisons and metaphors

SQL vs. NoSQL side by sideCPU caches explained as a kitchen

Interactive, exportable

  • Hover any box, pin or wire for details.
  • Click a code node to open the file, or a photo credit to open its source.
  • Export as SVG or PNG, fonts included: your system's save dialog asks where to put the file.
  • Fullscreen where the host supports it.

Install

Where do you use Claude? Sketchy comes two ways, and both can be installed side by side:

  • In the chat (web, desktop and mobile): the skill. Nothing to install locally.
  • While coding (Claude Code in the desktop app or terminal): the extension, which adds photo labeling, SVG and PNG export and click-to-open files.

Claude chat (web, desktop and mobile)

The skill draws right in the chat, with no server:

  1. Download sketchy-skill-<version>.zip from the latest release.
  2. In Claude, open Settings → Capabilities → Skills and upload the zip.
  3. Ask for a drawing in any chat.

Claude writes the scene, and the chat's inline visualization loads Sketchy's browser bundle from jsDelivr, which serves it from this repository's cdn branch. The skill follows the current minor version, so it picks up fixes without being uploaded again. To run exactly the code you reviewed, use sketchy-skill-<version>-pinned.zip instead: it loads the bundle from a fixed commit of the cdn branch and checks it with a Subresource Integrity hash, so the browser refuses any other file. It does not pick up fixes; upload the next pinned zip to update. Photo labeling and opening files from a drawing need your computer, so they stay in the desktop extension.

Claude desktop app (Code tab)

  1. Download the .mcpb file for your platform from the latest release (macOS on Apple Silicon, Windows or Linux).
  2. Double-click it (or drag it into Settings → Extensions) and confirm.
  3. Optional: in the extension settings choose your editor and where Sketchy stores its data.
  4. Open the Code tab and start a session. Drawings appear inline next to Claude's answer.

The Chat tab does not display views from locally installed extensions; use the skill above there.

The photo-labeling model is not part of the download. The first time Claude labels a photo, Sketchy asks you to pick a model size:

ModelDownloadMemoryNotes
Small~280 MB~1 GBRecommended. Printed text, distinct parts
Medium~830 MB~2.5 GBBetter grounding of small parts
Large~3.1 GB~4.5 GBMost precise

Claude Code in the terminal

The terminal claude does not use desktop extensions, so register Sketchy once for all your projects:

git clone https://github.com/ddkbs/sketchy.git
cd sketchy && npm install && npm run build
claude mcp add sketchy --scope user -- node "$PWD/dist/index.js"

Run claude mcp list to check that it is connected.

Other MCP clients

Sketchy is a standard MCP server and works in any client that supports MCP Apps:

{
  "mcpServers": {
    "sketchy": {
      "command": "node",
      "args": ["/path/to/sketchy/dist/index.js"],
      "env": { "SKETCHY_EDITOR": "cursor" }
    }
  }
}

Try it

  • "What happens when I open a web page? Walk me through it."
  • "How does an LLM pick the next word?"
  • "Explain the architecture of /path/to/my/repo, then walk me through one request."
  • "How is this sketch wired?" followed by your .ino file
  • "Show me a photo of a Raspberry Pi and label the ports."
  • "Compare TCP and UDP."
  • "Explain CPU caches with an everyday metaphor."

The same patterns are available as prompts: explain-structure, explain-flow, compare, metaphor, explain-repo and explain-circuit.

How it works

Claude describes the scene (extension: tools like sketch, place_part, label;
                            skill: the same scene as JSON in an inline widget)
          ↓
Scene: nodes, groups, parts, wires, labels, photos, steps — no coordinates
          ↓
Layout engine (elkjs): positions, orthogonal routing, collision-free callouts
          ↓
Viewer: hand-drawn rendering with rough.js, hover, steps, export

Every feature fills the same scene, and a single viewer renders it. The visual style lives in the renderer, so every drawing looks consistent no matter what Claude asks for. The extension runs layout in its server process and shows the viewer as an MCP App; the skill runs the same code in the browser from a bundle on jsDelivr.

Tools
ToolPurpose
sketchDraw a whole scene in one call, in the compact line syntax
search_partsElectronic part types and their pins
find_image, locate, choose_modelPhoto search, local grounding, model setup

A scene is a few short lines: browser Browser @globe, browser -> server HTTPS, step Request: The browser asks | browser browser->server. Setting SKETCHY_FORMAT=json restores the JSON sketch tool and the incremental tools of earlier versions (add_node, add_edge, place_part, label, render, …).

Follow-ups

Ask Claude to change a drawing ("add the cache and the call back to the router") and it sends the scene again with the same ids. Sketchy keeps the order and places of everything the earlier drawing already showed and fits the new parts in around them, so before and after stay comparable, also when a back-edge closes a cycle.

Token usage

Does a drawing cost more than a text answer? We asked Claude Sonnet to explain five topics (DNS, git branches, transformers, the TLS handshake, an Arduino button circuit), in plain text and with Sketchy, and read the exact usage Claude Code reports. Version 0.1.6 introduced the compact scene format; the JSON column is the format before it.

Average per answer, fresh conversationPlain textSketchy, JSON (≤ 0.1.5)Sketchy, compact (0.1.6)
Output tokens (what Claude writes)9621,168686 (−29% vs. text)
Tool definitions–~4,100~500
Cost on Sonnet list prices~$0.034~$0.059~$0.043

Over a whole session the compact format is cheaper than plain text. Six questions in a row, each variant in its own session, mean of two runs:

Answers in the sessionPlain textSketchy, JSONSketchy, compact
1$0.04$0.07$0.05
3$0.21$0.27$0.20
6$0.61$0.75$0.58
  • Claude writes less for a drawing than for text. Layout and drawing happen in Sketchy and cost no tokens.
  • Every answer stays in the history. Shorter answers keep it small, so each follow-up question costs less than after a text answer.
  • A tool call adds a turn that re-sends the context, mostly from the cache at a tenth of the price; this is why the very first answer still costs a little more than text.

Measured on November 2, 2026 in Claude Code with an empty project. Run it yourself with npm run build && node scripts/token-benchmark.mjs.

Configuration

VariableDefaultDescription
SKETCHY_EDITORvscodeEditor for file links: vscode, cursor, windsurf, vscode-insiders, zed
SKETCHY_PHOTOSonoff disables photo search and labeling
SKETCHY_DATA_DIR~/.sketchyModels, cached photos and the local SQLite database
SKETCHY_EXPORT_DIR~/DownloadsFolder the save dialog opens in, and where exports go when no dialog is available
SKETCHY_FORMATcompactjson restores the JSON scene tools of earlier versions

Development

Requires Node.js 20 or later.

npm install
npm run build      # part catalog, server and viewer
npm test
npm run preview    # viewer with sample scenes at http://localhost:5173/preview.html
npm run pack       # .mcpb bundle for the current platform
npm run build:skill  # chat skill zip
npm run build:web    # browser bundle that the skill loads

See CONTRIBUTING.md for the project layout.

License

MIT © ddkbs. Sketchy builds on open-source work listed in THIRD_PARTY_NOTICES.md.

// faq

What is sketchy?

A layout engine for LLM diagrams: Claude says what to draw, Sketchy figures out where. Hand-drawn, interactive, no overlapping boxes.. It is open-source on GitHub.

Is sketchy free to use?

sketchy is open-source under the MIT license, so it is free to use.

What category does sketchy belong to?

sketchy is listed under mcp-servers in the Claudeers registry of Claude-compatible tools.

16 views
★ 491 stars
unclaimed
updated 18 days ago

// embed badge

sketchy on Claudeers
[![Claudeers](https://claudeers.com/api/badge/sketchy.svg)](https://claudeers.com/sketchy)

// retro hit counter

sketchy hit counter
[![Hits](https://claudeers.com/api/counter/sketchy.svg)](https://claudeers.com/sketchy)

// reviews

// guestbook

0/500

// related in MCP Servers

🔓

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete…

// mcp-serversf/⟨HTML⟩★ 177,810◷ NOASSERTION[ claude ]
🔓

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

// mcp-serversfarion1231/⟨Rust⟩★ 155,814◷ MIT[ claude ]
🔓

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

// mcp-serversJuliusBrussee/⟨JavaScript⟩★ 117,780◷ MIT[ claude ]
🔓

An open-source AI agent that brings the power of Gemini directly into your terminal.

// mcp-serversgoogle-gemini/⟨TypeScript⟩★ 108,744◷ Apache-2.0[ claude ]
→ see how sketchy connects across the ecosystem