Processing MCP Server
An MCP server that enables AI assistants to create and run Processing sketches directly through natural language commands.
README
Processing MCP Server
🎨 Create visual art and games with AI - An MCP (Model Context Protocol) server that enables AI assistants to create and run Processing sketches directly through natural language commands.
⭐ Give us a star if you find this useful!
🎥 Demo Video
Watch the demo video here - See it in action!
🚀 Quick Setup
-
Clone this repository:
git clone https://github.com/twelve2five/processing-mcp-server.git cd processing-mcp-server -
Install dependencies:
uv pip install fastmcp # or pip install fastmcp -
Configure Claude Desktop (see Configuration section below)
-
Restart Claude and start creating!
Features
- 🚀 Create and run Processing sketches from AI conversations
- 💾 Automatically saves sketches with timestamps
- ⚙️ Configurable Processing executable path and save location
- 🤖 Simple tool interface for AI assistants
- 🎮 Includes 6 ready-to-run demos (particles, 3D art, games, and more!)
Installation
Prerequisites
- Python 3.8+
- Processing installed on your system
uvpackage manager (or use pip)- Claude Desktop app
Step 1: Clone the Repository
git clone https://github.com/twelve2five/processing-mcp-server.git
cd processing-mcp-server
Step 2: Install Dependencies
Install via uv
uv pip install fastmcp
Install via pip
pip install fastmcp
Step 3: Configure Claude Desktop
See the Configuration section below to add the server to your Claude Desktop config.
Configuration
The server can be configured in two ways:
1. Environment Variables
Set these environment variables before running the server:
PROCESSING_PATH: Path to your Processing executablePROCESSING_SAVE_LOCATION: Directory where sketches will be saved
2. Claude Desktop Configuration
Add this to your Claude Desktop config file:
Windows (%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"processing": {
"command": "uv",
"args": [
"run",
"C:\\path\\to\\processing-mcp-server\\processing_mcp_server.py"
],
"env": {
"PROCESSING_PATH": "C:\\Program Files\\Processing\\Processing.exe",
"PROCESSING_SAVE_LOCATION": "C:\\Users\\YourUsername\\Documents\\Processing\\sketches"
}
}
}
}
macOS (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"processing": {
"command": "uv",
"args": [
"run",
"/path/to/processing-mcp-server/processing_mcp_server.py"
],
"env": {
"PROCESSING_PATH": "/Applications/Processing.app/Contents/MacOS/Processing",
"PROCESSING_SAVE_LOCATION": "~/Documents/Processing/sketches"
}
}
}
}
Linux (~/.config/Claude/claude_desktop_config.json):
{
"mcpServers": {
"processing": {
"command": "uv",
"args": [
"run",
"/path/to/processing-mcp-server/processing_mcp_server.py"
],
"env": {
"PROCESSING_PATH": "/usr/bin/processing",
"PROCESSING_SAVE_LOCATION": "~/Documents/Processing/sketches"
}
}
}
}
Note: Replace /path/to/processing-mcp-server/ with the actual path where you cloned the repository.
3. Restart Claude Desktop
After updating the configuration file, restart Claude Desktop for the changes to take effect.
Usage Examples
Once configured, you can ask your AI assistant to:
🎯 Simple Animations
- "Create a Processing sketch that draws a bouncing ball"
- "Make a colorful spiral animation"
- "Draw a clock that shows the current time"
✨ Particle Effects
- "Create a particle system that follows my mouse"
- "Make fireworks that explode when I click"
- "Generate a starfield simulation"
🎮 Games
- "Build a Snake game"
- "Create a Pong clone"
- "Make a simple maze game"
🎨 Generative Art
- "Create a generative art piece with flowing waves"
- "Make a 3D rotating geometric shape"
- "Generate the Matrix digital rain effect"
Included Examples
Check out the /examples folder for ready-to-run demos:
- bouncing_ball.pde - Classic animation with trail effects
- particle_system.pde - Interactive particles following your mouse
- 3d_geometric_art.pde - Mesmerizing 3D shapes with rainbow colors
- matrix_rain.pde - The iconic Matrix digital rain effect
- wave_art.pde - Beautiful animated wave patterns
- snake_game.pde - Fully playable Snake game
The AI will use the run_processing_java_cli tool to create and launch your sketch.
Available Tools
run_processing_java_cli
Creates and runs a Processing sketch.
Parameters:
java_code(required): The Processing sketch codeprocessing_path(optional): Override the default Processing executable pathsave_location(optional): Override the default save location
get_processing_config
Returns the current server configuration.
Default Paths
If no configuration is provided, the server uses these defaults:
- Processing Path:
processing(assumes Processing is in your system PATH) - Save Location:
~/Documents/Processing/sketches
Troubleshooting
Server not showing up in Claude
Make sure to restart Claude Desktop after updating the configuration file.
Processing not found
If you get a "Processing executable not found" error:
- Ensure Processing is installed
- Check that the path in your configuration is correct
- On Windows, use double backslashes (
\\) in the path - On macOS, the path should point to the executable inside the .app bundle
Permission errors
Make sure the save location directory exists and is writable by your user.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT License - see LICENSE file for details
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。