AsepriteMCP
Documentation
Aseprite MCP Tools v2.0
A powerful Python MCP (Model Context Protocol) server for programmatic interaction with Aseprite, featuring enhanced error handling, configuration management, batch processing, and more!
🚀 What's New in v2.0
- 🛡️ Comprehensive Error Handling: Custom exceptions with detailed, actionable error messages
- 🔧 Configuration Management: Pydantic-based settings with JSON/YAML support
- 📝 Advanced Logging: Structured logging with performance metrics
- 🎨 Palette Management: Create, apply, and extract color palettes
- ⚡ Batch Processing: Process multiple files in parallel
- 🏗️ Lua Script Builder: Clean, type-safe Lua script generation
- 🔒 Enhanced Security: Input validation and path traversal protection
- 🧪 Full Test Coverage: Comprehensive unit tests
📋 Features
Core Drawing Tools
- Canvas Operations: Create sprites, add layers and frames
- Drawing Tools: Pixels, lines, rectangles, circles, and fill operations
- Export Tools: Export to various formats with scaling and layer support
New Palette Tools (v2.0)
- Preset Palettes: GameBoy, NES, PICO-8, CGA, Monochrome, Sepia
- Custom Palettes: Create and apply custom color schemes
- Palette Extraction: Extract colors from existing images
- Color Remapping: Replace colors throughout sprites
Batch Processing (v2.0)
- Batch Resize: Resize multiple sprites maintaining aspect ratio
- Batch Export: Convert multiple files to different formats
- Batch Palette Apply: Apply palettes to multiple files
- Custom Scripts: Run Lua scripts on file sets
🔧 Installation
Requirements
- Python 3.13+
- Aseprite (must be installed separately)
Claude Desktop Configuration
Using UV (Recommended)
{
"mcpServers": {
"aseprite": {
"command": "/opt/homebrew/bin/uv",
"args": [
"--directory",
"/path/to/aseprite-mcp",
"run",
"-m",
"aseprite_mcp"
],
"env": {
"ASEPRITE_PATH": "/path/to/aseprite"
}
}
}
}Using Python
{
"mcpServers": {
"aseprite": {
"command": "python",
"args": ["-m", "aseprite_mcp"],
"cwd": "/path/to/aseprite-mcp",
"env": {
"ASEPRITE_PATH": "/path/to/aseprite"
}
}
}
}Install Dependencies
pip install -r requirements.txt⚙️ Configuration
Environment Variables
export ASEPRITE_PATH="/Applications/Aseprite.app/Contents/MacOS/aseprite"
export ASEPRITE_MCP_LOG_LEVEL="INFO"Configuration File (config.json)
{
"aseprite_path": "/path/to/aseprite",
"canvas": {
"max_width": 10000,
"max_height": 10000
},
"batch": {
"max_parallel_jobs": 4,
"continue_on_error": true
},
"log_level": "INFO",
"security": {
"allowed_directories": ["/home/user/sprites"],
"max_file_size": 104857600
}
}Configuration File (config.yaml)
aseprite_path: /path/to/aseprite
canvas:
max_width: 10000
max_height: 10000
default_color_mode: RGBA
batch:
max_parallel_jobs: 4
continue_on_error: true
log_level: INFO
security:
allowed_directories:
- /home/user/sprites
max_file_size: 104857600📖 Usage Examples
Basic Drawing Operations
# Create a new sprite
await create_canvas(320, 240, "my_sprite.aseprite")
# Draw pixels
await draw_pixels("my_sprite.aseprite", [
{"x": 10, "y": 10, "color": "FF0000"}, # Red
{"x": 11, "y": 10, "color": "00FF00"}, # Green
{"x": 12, "y": 10, "color": "0000FF"} # Blue
])
# Draw shapes
await draw_rectangle("my_sprite.aseprite", 50, 50, 100, 80, "FFFF00", fill=True)
await draw_circle("my_sprite.aseprite", 160, 120, 30, "FF00FF", fill=False)
await draw_line("my_sprite.aseprite", 0, 0, 320, 240, "FFFFFF", thickness=2)
# Fill area
await fill_area("my_sprite.aseprite", 100, 100, "00FFFF", tolerance=10)Layer and Frame Management
# Add a new layer
await add_layer("my_sprite.aseprite", "Background")
# Add animation frames
await add_frame("my_sprite.aseprite", after_frame=0)Palette Operations
# Apply preset palette
await apply_preset_palette("my_sprite.aseprite", "gameboy")
# Available presets: gameboy, gameboy-pocket, nes, pico-8, cga, monochrome, sepia
# Create custom palette
await create_palette("my_sprite.aseprite", [
"264653", "2A9D8F", "E9C46A", "F4A261", "E76F51"
])
# Extract palette from image
await extract_palette_from_image("reference.png", max_colors=16)
# Get palette information
await get_palette_info("my_sprite.aseprite")
# Remap colors
await remap_colors("my_sprite.aseprite", {
"FF0000": "00FF00", # Red to Green
"0000FF": "FFFF00" # Blue to Yellow
})Export Operations
# Export single file
await export_sprite("my_sprite.aseprite", "output.png", scale=2.0)
# Export with frame range
await export_sprite("animation.aseprite", "frames.gif", frame_range="1-10")
# Export each layer separately
await export_layers("my_sprite.aseprite", "layers/", format="png")Batch Processing
# Resize multiple sprites
await batch_resize(
input_dir="sprites/",
output_dir="sprites_small/",
scale=0.5,
file_pattern="*.aseprite"
)
# Export batch to PNG
await batch_export(
input_dir="sprites/",
output_dir="exports/",
format="png",
scale=2.0
)
# Apply palette to multiple files
await batch_apply_palette(
input_dir="sprites/",
palette_file="my_palette.aseprite",
create_backup=True
)
# Run custom Lua script on multiple files
await batch_process_custom(
input_dir="sprites/",
lua_script="app.activeSprite:flatten()",
output_dir="flattened/"
)🏗️ Architecture
Project Structure
aseprite-mcp/
├── aseprite_mcp/
│ ├── core/
│ │ ├── commands.py # Aseprite command execution
│ │ ├── config.py # Configuration management
│ │ ├── exceptions.py # Custom exceptions
│ │ ├── logging.py # Logging system
│ │ ├── lua_builder.py # Lua script builder
│ │ └── validation.py # Input validation
│ └── tools/
│ ├── batch.py # Batch processing
│ ├── canvas.py # Canvas operations
│ ├── drawing.py # Drawing tools
│ ├── export.py # Export functions
│ └── palette.py # Palette management
├── tests/ # Unit tests
├── examples/ # Example scripts
└── config.example.yaml # Configuration exampleError Handling
try:
result = await create_canvas(-100, 200, "test.aseprite")
except ValidationError as e:
print(f"Validation failed: {e}")
except AsepriteError as e:
print(f"Aseprite error: {e}")Lua Script Builder
from aseprite_mcp.core.lua_builder import LuaBuilder
builder = LuaBuilder()
builder.create_sprite(200, 200)
builder.begin_transaction()
builder.set_color("FF0000")
builder.for_loop("i", 0, 10)
builder.draw_pixel("i * 10", "i * 10")
builder.end_loop()
builder.end_transaction()
builder.save_sprite("output.aseprite")
script = builder.build() # Returns clean Lua code🧪 Testing
Run all tests:
pytest tests/ -vRun specific test:
pytest tests/test_validation.py -vRun demo script:
python examples/demo_improvements.py📝 Logging
Logs include:
- Operation tracking
- Performance metrics
- Error details with context
- Structured JSON output (optional)
Example log:
2024-06-11 10:30:45 - aseprite_mcp - INFO - Operation: create_canvas
2024-06-11 10:30:45 - aseprite_mcp - INFO - Canvas created successfully
2024-06-11 10:30:45 - aseprite_mcp - INFO - Performance: create_canvas took 0.234s🤝 Contributing
1. Fork the repository
2. Create a feature branch
3. Follow the coding standards:
4. Submit a pull request
📄 License
MIT License - see LICENSE file for details
🙏 Credits
- Original implementation: Divyansh Singh
- v2.0 improvements: Enhanced error handling, configuration, batch processing, and more
📚 Additional Resources
- Aseprite API Documentation
- MCP Documentation
- IMPROVEMENTS.md - Detailed v2.0 changes
Frequently asked questions
What is AsepriteMCP?
AsepriteMCP is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install AsepriteMCP?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is AsepriteMCP open source?
Yes — it is hosted on GitHub at https://github.com/ext-sakamoro/AsepriteMCP and has 10 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Python SQL Parser and Transpiler
MCP server that interacts with Obsidian via the Obsidian rest API community plugin
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP