explaingit

abidoo22/pixelorama-mcp

★ 2TypeScriptAudience · vibe coderComplexity · 3/5ActiveLicenseSetup · moderate

TLDR

MCP server that lets an AI assistant draw pixel art inside Pixelorama by exposing 30+ drawing, layer, palette, and animation tools as MCP calls.

Mindmap

mindmap
  root((Pixelorama-MCP))
    Inputs
      Plain English prompts
      MCP client config
    Outputs
      Pixel art sprites
      Animated GIFs
      Multi-layer canvases
    Use Cases
      AI sprite generation
      Procedural pixel art
      Agentic drawing scripts
    Tech Stack
      TypeScript
      Node.js
      MCP
      Pixelorama
      GDScript

Things people build with this

USE CASE 1

Ask Claude Desktop to draw a 32x32 sword sprite with specific colours without opening Pixelorama yourself.

USE CASE 2

Run an agent loop that generates a full animation by adding frames and exporting a GIF from one prompt.

USE CASE 3

Wire Cursor to Pixelorama so a coding agent can create game asset placeholders during development.

USE CASE 4

Write custom JS drawing scripts that batch-render sprites using the agentic drawing playbook.

Tech stack

TypeScriptNode.jsMCPPixeloramaGDScript

Getting it running

Difficulty · moderate Time to first run · 30min

You need Pixelorama 1.1.10 installed locally plus a Godot plugin .pck file enabled inside it before the MCP server can do anything.

MIT license, you can use, modify, and redistribute the code freely as long as you keep the copyright notice.

In plain English

Pixelorama-MCP, also called pix-MCP, is a small server that lets an AI assistant draw pixel art inside Pixelorama, a free pixel art editor. You type a request in plain English, like asking for a 32 by 32 sword with a golden blade and brown handle, and the AI uses this server to do the actual drawing inside the editor. The idea is that you do not need any drawing skills yourself. The project sits in the middle of two programs. On one side is the AI client, such as Claude Desktop, Cursor, or another tool that speaks the Model Context Protocol, a shared way for AI assistants to talk to outside software. On the other side is Pixelorama, with a small plugin installed inside it. The pix-MCP server is written in TypeScript and runs on Node.js. It receives instructions from the AI and forwards them to the Pixelorama plugin over a local HTTP connection. The README lists more than thirty drawing tools that the AI can call, covering pixels, lines, rectangles, ellipses, polygons, and flood fill. It can also create and rename layers, change opacity and blend modes, set colours, build palettes, and pick colours from the canvas. There is animation support for adding frames, setting durations, and exporting GIFs, plus selection and transform actions like move, resize, flip, and rotate. A helper called generate_sprite chains several of these steps together from a single text prompt. To use it, you clone the repository, install Node.js packages, build the server, then install a plugin file into Pixelorama and restart the editor. You then point your AI client at the built server file through a configuration entry. The README links to a getting started guide, a tool reference, a plugin setup guide, and an agentic drawing playbook for developers who want to write their own drawing scripts. The licence is MIT.

Copy-paste prompts

Prompt 1
Set up Pixelorama-MCP on my machine, install the Godot plugin into Pixelorama, and wire it into Claude Desktop with the right config block.
Prompt 2
Use Pixelorama-MCP to create a 32x32 pixel sword with a golden blade and brown handle on a new layer.
Prompt 3
Use generate_sprite from Pixelorama-MCP to build a 4-frame walking animation of a green slime and export it as a GIF.
Prompt 4
Read the Agentic Drawing Playbook in this repo and write a custom JS script that draws a shaded coin with a drop shadow.
Prompt 5
Add a new MCP tool to Pixelorama-MCP that fills a region with a dithered gradient between two colours.
Open on GitHub → Explain another repo

Generated 2026-05-22 · Model: sonnet-4-6 · Verify against the repo before relying on details.