pixel-mcp
An MCP server that enables AI coding agents to create pixel art programmatically by providing canvas manipulation tools and PNG export.
README
pixel-mcp
An MCP (Model Context Protocol) server that lets AI coding agents (Claude Code, Cursor, Windsurf, etc.) create pixel art programmatically. No daemon, no sockets, no Go runtime — just a lightweight TypeScript server that runs via npx.
Install
Use with Claude Code
Run this from your project directory:
claude mcp add pixel-art npx -- pxcli-mcp --export-dir ./assets/sprites
This registers the server in Claude Code's config scoped to your project. Verify it's connected with /mcp.
Use with any MCP client
npx pxcli-mcp --export-dir ./output
From source
npm install
npm run build
node dist/index.js --export-dir ./output
Quick start
Once configured, Claude (or any MCP client) can use these tools directly:
create_canvas(name: "hero", width: 16, height: 16)
fill_rect(canvas: "hero", x: 0, y: 0, width: 16, height: 16, color: "black")
set_pixel(canvas: "hero", x: 8, y: 4, color: "#ff0000")
draw_line(canvas: "hero", x1: 0, y1: 15, x2: 15, y2: 15, color: "white")
export_png(canvas: "hero", filename: "hero.png")
Tools
| Tool | Description |
|---|---|
create_canvas |
Create a named canvas with given dimensions (max 256x256) |
list_canvases |
List all active canvases and their sizes |
set_pixel |
Set a single pixel color |
get_pixel |
Read a pixel's color |
fill_rect |
Fill a rectangle with a solid color |
draw_line |
Draw a line between two points (Bresenham's algorithm) |
clear |
Clear entire canvas to a color (default: transparent) |
export_png |
Export canvas to a PNG file |
undo |
Undo the last drawing operation |
redo |
Redo the last undone operation |
All drawing tools accept a canvas parameter (defaults to "default"), so you can work on multiple sprites simultaneously.
Color formats
- Hex:
#rgb,#rrggbb,#rrggbbaa - Named:
red,green,blue,white,black,transparent,yellow,cyan,magenta,orange,purple,gray,grey,pink,brown,lime,navy,teal,maroon,olive
CLI options
| Flag | Description |
|---|---|
--export-dir <path> |
Directory for exported PNGs (defaults to CWD) |
Playground (live preview)
The repo includes viewer.html — a browser-based playground for watching pixel art being drawn in real time.
- Serve the file locally:
npx serve . - Open
http://localhost:3000/viewer.htmlin your browser
The playground has two columns:
- Left: Scaled pixel canvas with coordinate tracker on hover
- Right: Prompt field, canvas settings (name, dimensions, scale, background, export dir), action buttons, and a live operation log
The canvas exposes global drawing functions (px, rect, line) that can be called from the browser console or via browser automation tools (e.g. Claude in Chrome). This makes it easy to visually verify pixel art as it's being drawn step by step.
Drawing from the browser console
// Set a red pixel at (10, 5)
px(10, 5, 255, 0, 0, 255)
// Fill a blue rectangle
rect(0, 0, 16, 16, 0, 0, 255, 255)
// Draw a green line
line(0, 0, 15, 15, 0, 255, 0, 255)
// Update status message
setStatus('Drawing complete!')
Development
npm install
npm run build
npm test # runs 22 tests (unit + MCP integration)
npm run dev # watch mode for TypeScript compilation
Credits
Inspired by and built on top of vossenwout/pixel-art-cli — thank you for the original Go daemon-based pixel art CLI that made this possible.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.