Pixelorama MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pixelorama MCP draw a small yellow star sprite at 4,4, then export it as a PNG"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pixelorama-mcp
Lets AI agents like Claude Code draw pixel art in Pixelorama through MCP.
It has two parts: a Pixelorama extension that runs inside the editor, and an MCP server that the agent talks to. The agent works on whatever is open in Pixelorama, you watch it happen on the canvas, and every change can be undone with Ctrl+Z like any other edit.
Drawing format
Agents draw with a character grid and a palette, which is far easier for a language model than coordinates:
{
"palette": { "o": "#7a4a12", "y": "#f2c230", "h": "#fff2a8" },
"rows": [
"..oooo..",
".ohyyyo.",
"oyyyyyyo",
".oyyyyo.",
"..oooo.."
],
"x": 4,
"y": 4
}Characters missing from the palette (like .) leave pixels alone. read_pixels returns existing art in the same format, so an agent can read a sprite, change it and write it back.
Related MCP server: Aseprite MCP
Tools
Tool | What it does |
| Size, frames, layers and the current cel |
| New canvas in a new tab |
| Open a |
| Draw a character grid |
| Fill a rectangle, or the whole cel |
| Erase a cel |
| Read pixels back as a character grid |
| Image of a frame, scaled up so the agent can see it |
| Add a layer or frame and select it |
| Change the current frame/layer |
| Save as |
| Export a frame, or all frames as a sprite sheet |
Frames are counted from 0, left to right. Layers are counted from 0 at the bottom.
Setup
Requires Pixelorama 1.2 (extension API 9) and Node.js 22 or newer.
git clone https://github.com/CyberIce2077/pixelorama-mcp.git ~/projects/pixelorama-mcp
cd ~/projects/pixelorama-mcp
npm install
npm run install-extensionnpm install builds the server and packs the extension into dist/PixeloramaMCP.zip. install-extension copies it into Pixelorama's extensions folder. You can also install the zip from Pixelorama's Preferences > Extensions.
Restart Pixelorama, enable Pixelorama MCP in Preferences > Extensions, then add the server to Claude Code:
claude mcp add pixelorama -- node ~/projects/pixelorama-mcp/dist/index.jsHow it works
agent <--stdio--> pixelorama-mcp server <--TCP 127.0.0.1:7651--> Pixelorama extensionThe extension listens on localhost only and speaks one JSON object per line. Any connection that sends something else, such as a web page trying to reach the port over HTTP, is dropped before a command runs.
The port is 7651. To change it, set PIXELORAMA_MCP_PORT for the server and PORT in extension/src/Extensions/PixeloramaMCP/Main.gd.
Limitations
Only pixel layers can be drawn on. Group, tilemap, 3D and audio layers are reported but not editable.
Commands act on the project in the active tab.
No brushes, selections or tools yet; drawing is pixels and rectangles.
License
MIT
Available Tools
13 toolsadd_frameA
Add an empty frame. By default it goes after the last frame.
Inputs: after.
add_layerB
Add a pixel layer. By default it goes on top of all layers.
Inputs: name, above.
clear_celB
Erase every pixel of one cel (a layer in a frame).
Inputs: frame, layer.
draw_pixelsA
Draw pixels from a character grid. Each string in rows is one row of pixels; each character is looked up in palette. Characters that are not in the palette (such as '.') leave the pixel unchanged, so map a character to "transparent" to erase. Example: palette {"o": "#e8a33d", "d": "#7a4a12"}, rows [".oo.", "oddo", ".oo."]. The whole call is one undo step in Pixelorama.
Inputs: rows (required), palette (required), x, y, +2 more.
export_pngA
Export the current frame, or all frames as a horizontal sprite sheet, to a PNG file. Layers are blended the same way Pixelorama shows them.
Inputs: path (required), frame, scale, all_frames.
fill_rectA
Fill a rectangle with one color. Leave out the position and size to fill the whole canvas.
Inputs: color (required), x, y, frame, +3 more.
get_imageA
Show a frame with all visible layers blended, scaled up with nearest-neighbour so pixels stay sharp.
Inputs: frame, scale.
get_projectA
Describe the project open in Pixelorama: size, frames, layers and the current cel.
Inputs: no named parameters.
new_projectB
Create a new, empty project in a new tab and switch to it.
Inputs: width (required), height (required), name.
open_fileA
Open a .pxo project or an image (png, jpg, webp, bmp, tga) in a new tab.
Inputs: path (required).
read_pixelsB
Read pixels of one cel as a character grid with a palette, in the same format draw_pixels takes. '.' is transparent. At most 16384 pixels per call.
Inputs: x, y, frame, layer, +2 more.
save_projectA
Save the current project as a .pxo file. Without a path it saves to where it was last saved.
Inputs: path.
select_celC
Make a frame/layer the current one in Pixelorama.
Inputs: frame, layer.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 13 tools
Each tool maps to a distinct action (draw, read, fill, clear, export, select), and descriptions clarify boundaries well. The only mild overlap is get_project (metadata description) versus get_image (rendered preview), but their descriptions make the distinction clear.
All 13 tools use a consistent snake_case verb_noun pattern (get_project, add_layer, draw_pixels, export_png, save_project). No mixing of conventions or vague single-word names.
13 tools sits squarely in the ideal 3-15 range and each one covers a distinct editing or project operation. Nothing feels padded or missing from a count perspective.
Project lifecycle (new/open/save/export) and drawing/reading are well covered, but the surface is create-only for structure: add_layer and add_frame exist with no delete_layer or remove_frame, and there is no layer/frame reordering, visibility, or undo control. Agents will hit dead ends when they need to remove or reorder content.
Related MCP Connectors
Pixel art for your game, from your coding agent. Generate sprites, items and tiles in your game's style (64 to 1024 px), make variants, reskins and N/E/S/W directions, then edit everything in a full pixel art editor that syncs into your project. Works with Claude, Claude Code, Cursor and ChatGPT; sign in with OAuth, no API key.
Turn images into pixel art, extract and remap palettes, and upscale sprites without blur.
Generate pixel art sprites, animations, 8-direction rotations and palettes for games.
Free pixel and tileset editor, no account: hand-edit sprites, animations and Wang tilesets in chat
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to create and manipulate pixel art by providing tools for drawing, layer management, and animation frame control. It supports exporting projects to PNG, GIF, and sprite sheet formats via the Model Context Protocol.2219Apache 2.0
- AlicenseCqualityBmaintenanceEnables AI assistants to control Aseprite for drawing and editing images through its API.591,009MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI to directly control Pixelorama for real-time 2D game asset creation, including layer-based pixel drawing, animation frames, automatic quality checks, and export of spritesheets, .pxo files, and Godot resources.-
- AlicenseBqualityCmaintenanceEnables an AI agent to create and edit pixel art directly in Aseprite — building sprites, layers, frames, animation tags and palettes, painting pixels and primitives, inspecting the rendered result, and exporting GIFs or sprite sheets. All work lands on real .aseprite files that can be opened and edited by hand.431MIT