Skip to main content

MCP server for generating SPINE2D animations from PSD files using natural language

Project description

SPINE2D Animation MCP Server

This Model Context Protocol (MCP) server provides tools for creating SPINE2D animations from PSD character files using natural language descriptions.

Overview

The SPINE2D Animation MCP server allows you to:

  1. Import PSD character files
  2. Automatically rig characters
  3. Generate animations using natural language descriptions
  4. Preview animations
  5. Export animations in various formats

Requirements

  • Python 3.6+
  • Required Python packages (installed automatically):
    • Flask
    • Pydantic
    • Pillow
    • PSD-Tools
    • OpenAI (for natural language processing)
    • Requests
    • Python-dotenv

Installation

  1. Clone this repository
  2. Run the installation script:
./install.sh

The installation script will:

  • Create necessary storage directories
  • Install Python dependencies
  • Configure MCP settings for VS Code
  • Optionally configure MCP settings for Claude Desktop

Usage

After installation, restart VS Code and/or Claude. You can then use the following tools through the MCP server:

Import PSD Character

Upload and process a PSD file:

Use: "Import my character from character.psd"

Parameters:

  • file_path: Path to the PSD file

Setup Character

Automatically rig a character that has been imported:

Use: "Set up rigging for my character"

Parameters:

  • character_id: Character ID from import_psd

Generate Animation

Create an animation from a text description:

Use: "Create a happy waving animation for my character"
Use: "Make my character jump with excitement"
Use: "Animate my character to run scared with sparkle effects"

Parameters:

  • character_id: Character ID
  • description: Animation description (e.g., "wave happily")

Preview Animation

Get a preview of the animation:

Use: "Show me a preview of the waving animation"

Parameters:

  • character_id: Character ID
  • animation_id: Animation ID

Export Animation

Export the final animation:

Use: "Export the jumping animation as a GIF"

Parameters:

  • character_id: Character ID
  • animation_id: Animation ID
  • format: Export format (json, png, gif)

Project Structure

spine2d-animation-mcp/
├── README.md             # This file
├── requirements.txt      # Python dependencies
├── install.sh            # Installation script
├── src/
│   ├── main.py           # Entry point
│   ├── server.py         # MCP server implementation
│   ├── psd_parser.py     # PSD parsing module
│   ├── animation_generator.py  # Animation generation module
│   └── spine2d_integration.py  # SPINE2D integration module
└── storage/              # Created during installation
    ├── characters/       # Imported character data
    ├── animations/       # Generated animations
    ├── rigs/             # Character rigs
    └── exports/          # Exported animations

How It Works

  1. PSD Import: The server parses a PSD file, extracts layers, and organizes them into a character structure.
  2. Character Rigging: The server analyzes the character structure and automatically creates bones, IK constraints, and skin attachments.
  3. Animation Generation: Natural language descriptions are parsed to extract animation type, emotion, and intensity. The server then applies these to animation templates.
  4. Animation Preview: The server generates a preview of the animation in GIF format.
  5. Animation Export: The server exports the animation in the requested format (JSON, PNG, or GIF).

Limitations

  1. The automatic rigging system is based on layer names and structure, which may require specific naming conventions for optimal results.
  2. The animation templates are predefined, so complex custom animations may require manual adjustment.
  3. The natural language processing is simplified in this implementation and may not capture all nuances of complex descriptions.

Future Improvements

  1. Improved natural language understanding using more advanced LLM integration
  2. More sophisticated automatic rigging with bone placement based on image analysis
  3. Expanded library of animation templates
  4. Real-time preview rendering
  5. More export formats and options

Documentation

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file iflow_mcp_naosen_spine2d_animation_mcp-0.1.4.tar.gz.

File metadata

  • Download URL: iflow_mcp_naosen_spine2d_animation_mcp-0.1.4.tar.gz
  • Upload date:
  • Size: 4.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_naosen_spine2d_animation_mcp-0.1.4.tar.gz
Algorithm Hash digest
SHA256 ea362ab28995a4da6777e1481cb0f71500481819858f2452815624282cf3204d
MD5 23665d5a3d8ba8102d0ca6015c4524fd
BLAKE2b-256 b59f8302d64f462447c8b259f025102e0952a00550c9321ec06fc38a72f5fb3b

See more details on using hashes here.

File details

Details for the file iflow_mcp_naosen_spine2d_animation_mcp-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_naosen_spine2d_animation_mcp-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 4.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_naosen_spine2d_animation_mcp-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 4bf0524f71c740e8a101ddee5636d649a50bbe988675a623a3a53b949e7c7701
MD5 1bbf659f1c56214fdb929004929b6b4b
BLAKE2b-256 8cdc8444f9fa1e44d08b8e04f1c4c6cb074280bac6c0589beb047d4e52b9c47c

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page