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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。