QusaiiSaleem/scenario-asset-mcp-public

Scenario Asset MCP Server

A Model Context Protocol (MCP) server for Unity game asset generation using Scenario.gg AI, designed for seamless integration with MCP clients like Claude Desktop, smithery-playground, and other MCP-compatible tools.

🎮 What This Does

This MCP server provides 10 comprehensive tools for generating Unity-ready game assets:

• Characters: Heroes, NPCs, enemies with multiple art styles
• Environments: Backgrounds, landscapes, interiors, skyboxes
• Props & Objects: Weapons, collectibles, furniture, vehicles
• UI Elements: Buttons, panels, frames with 9-slice support
• Textures: PBR materials, seamless textures, surface maps
• Icons: UI icons, logos, symbols with multiple sizes
• Asset Management: Search, retrieve, and manage generated assets

✨ Key Features

• 🔌 MCP Protocol Compliant: Works with any MCP client
• 🎨 Unity-Optimized: PNG+Alpha, proper import settings, organized folders
• ⚡ Performance Focused: WebGL/Mobile optimized, <300ms response times
• 🛡️ Production Ready: Rate limiting, security headers, error handling
• 📱 Multi-Platform: Supports various art styles and target platforms
• 🔄 Batch Processing: Generate multiple variations in one request

🚀 Quick Start

Prerequisites

• Cloudflare Workers account
• Scenario.gg API account
• Supabase account (for asset storage)
• Wrangler CLI

1. Clone and Setup

git clone https://github.com/yourusername/scenario-asset-mcp.git
cd scenario-asset-mcp

2. Install Dependencies

npm install
# or
yarn install

3. Configure Environment

# Copy example environment file
cp wrangler.toml.example wrangler.toml

# Set your secrets
wrangler secret put SCENARIO_API_KEY
wrangler secret put SCENARIO_API_SECRET
wrangler secret put SUPABASE_URL
wrangler secret put SUPABASE_ANON_KEY
wrangler secret put SUPABASE_SERVICE_ROLE_KEY

4. Deploy

wrangler deploy

Your MCP server will be available at: https://your-worker-name.your-subdomain.workers.dev

🔧 Configuration

Required Secrets

Set these using wrangler secret put <SECRET_NAME>:

Optional Configuration

Edit wrangler.toml to customize:

[vars]
ENVIRONMENT = "production"
LOG_LEVEL = "info"
MAX_CONCURRENT_REQUESTS = "20"
RATE_LIMIT_MAX_REQUESTS = "100"
RATE_LIMIT_WINDOW_MS = "60000"

🛠️ Available Tools

Asset Generation Tools

generate_characters

Generate character sprites for your Unity game.

{
  "name": "generate_characters",
  "arguments": {
    "prompt": "medieval knight with silver armor",
    "character_type": "hero",
    "art_style": "cartoon",
    "num_variations": 2,
    "tags": ["fantasy", "armor"]
  }
}

generate_environments

Create backgrounds and environment assets.

{
  "name": "generate_environments", 
  "arguments": {
    "prompt": "desert oasis with palm trees",
    "environment_type": "background",
    "art_style": "realistic",
    "time_of_day": "sunset",
    "resolution": "wide"
  }
}

generate_props_objects

Generate game objects like weapons, collectibles, furniture.

{
  "name": "generate_props_objects",
  "arguments": {
    "prompt": "golden sword with gemstones",
    "object_type": "weapon",
    "rarity": "legendary",
    "transparency": true
  }
}

generate_ui_system

Create UI elements with 9-slice support.

{
  "name": "generate_ui_system",
  "arguments": {
    "prompt": "futuristic blue button with glow",
    "ui_type": "button",
    "ui_style": "sci-fi",
    "state_variants": true,
    "nine_slice": true
  }
}

generate_textures_materials

Generate PBR textures and materials.

{
  "name": "generate_textures_materials",
  "arguments": {
    "prompt": "weathered stone brick wall",
    "texture_type": "complete_pbr",
    "material_type": "stone",
    "seamless": true
  }
}

generate_icons_symbols

Create icons and symbols for UI.

{
  "name": "generate_icons_symbols",
  "arguments": {
    "prompt": "health potion icon with red liquid",
    "icon_type": "ui_icon",
    "icon_style": "filled",
    "size_variants": true
  }
}

Asset Management Tools

search_assets

Search previously generated assets.

{
  "name": "search_assets",
  "arguments": {
    "type": "character",
    "tags": ["fantasy"],
    "limit": 10
  }
}

get_asset_details

Get detailed information about an asset.

{
  "name": "get_asset_details",
  "arguments": {
    "asset_id": "uuid-here"
  }
}

list_scenario_models

List available AI models.

{
  "name": "list_scenario_models",
  "arguments": {}
}

delete_asset

Delete an asset (use with caution).

{
  "name": "delete_asset",
  "arguments": {
    "asset_id": "uuid-here",
    "confirm": true
  }
}

🔌 MCP Client Integration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "scenario-assets": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/server-fetch",
        "https://your-worker.workers.dev/mcp"
      ]
    }
  }
}

Smithery Playground

Connect directly using the server URL:

https://your-worker.workers.dev/mcp

Other MCP Clients

Use the standard MCP endpoints:

• MCP Protocol: POST /mcp
• Server Discovery: GET /
• Health Check: GET /health
• Streaming: GET /mcp/stream

🏗️ Architecture

Technology Stack

• Runtime: Cloudflare Workers (Edge computing)
• Protocol: MCP (Model Context Protocol) JSON-RPC 2.0
• AI Generation: Scenario.gg API
• Storage: Supabase (PostgreSQL + File Storage)
• Format: Unity-optimized PNG+Alpha assets

Request Flow

MCP Client → Cloudflare Worker → Scenario API → Asset Generation
                ↓
         Supabase Storage ← Unity Import ← Asset Processing

Performance Features

• Edge Computing: Global CDN with <50ms latency
• Concurrent Processing: Up to 20 parallel requests
• Smart Caching: Asset metadata and model listings
• Rate Limiting: 100 requests/minute per client
• Timeout Management: 30s default, 120s for generation

🧪 Testing

Local Development

# Install dependencies
npm install

# Start local development server
wrangler dev

# Test endpoints
curl http://localhost:8787/health

Testing MCP Protocol

# Test initialization
curl -X POST http://localhost:8787/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{}},"id":1}'

# Test tools list
curl -X POST http://localhost:8787/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":2}'

Unity Integration Testing

1. Generate test assets using the MCP tools
2. Import into Unity project
3. Verify PNG+Alpha format and transparency
4. Test sprite pivot points and physics shapes
5. Validate performance on target platform

📚 Documentation

API Reference

• MCP Protocol Specification
• Scenario.gg API Docs
• Cloudflare Workers Docs

Unity Integration

• Unity Sprite Import Settings
• Unity 9-Slice Sprites
• Unity Asset Workflow

🤝 Contributing

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'Add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open a Pull Request

Development Guidelines

• Follow the existing code style
• Add tests for new features
• Update documentation
• Ensure Unity compatibility
• Test with multiple MCP clients

📝 License

This project is licensed under the MIT License - see the file for details.

🆘 Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Documentation: Wiki

🙏 Acknowledgments

• Model Context Protocol for the excellent protocol specification
• Scenario.gg for the powerful AI generation API
• Cloudflare Workers for the serverless platform
• Unity Technologies for the game engine integration

🚀 Roadmap

• Resource system for asset templates
• Prompt system for common generation patterns
• Batch generation workflows
• Unity Editor plugin
• Asset versioning and history
• Collaborative asset sharing
• Custom model training integration

Made with ❤️ for Unity game developers using AI-powered asset generation