aws-nova-canvas-mcp 0.1.2

An MCP server that allows you to generate and edit images using the Nova Canvas model of Amazon Bedrock

AWS Nova Canvas MCP Server

An MCP server that allows you to generate and edit images using the Nova Canvas model of Amazon Bedrock.

Features

• Text to Image
• Image Inpainting
• Image Outpainting
• Image Variation
• Image Conditioning
• Color Guided Generation
• Background Removal
• Show Image Thumbnails

Installation

Claude Desktop Setup

1. Clone the repository

git clone https://github.com/yunwoong/aws-nova-canvas-mcp.git

2. Configure Claude Desktop
   • Click on Claude > Settings from the Claude Desktop menu.
   • When the popup appears, select Developer from the left menu, and click the Edit Settings button.
   • This will open a folder containing the settings file. The name of this settings file is:
   • claude_desktop_config.json

3. Add the following content to the settings file (Python version):

   • python version

     "nova-canvas": {
       "command": "uv",
       "args": [
         "--directory",
         "Path to clone folder",
         "run",
         "server.py"
       ],
       "env": {
         "AWS_PROFILE": "YOUR_AWS_PROFILE"
       }
     }
     

     ✅ Only AWS_PROFILE is required. Other variables like AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION, and PORT are optional and not necessary if your AWS profile is set correctly.

     ​ ⚙️ If the setup is completed successfully, you can see that the "nova-canvas" item has been added in Claude > Settings > Developer tab. ⚠️ Important: MCP settings only work on the Claude desktop app, not the Claude web browser version

Image Save Location

By default, all generated or edited images will be saved in the following directory:

• macOS / Linux: ~/Desktop/aws-nova-canvas
• Windows: C:\Users\YourUsername\Desktop\aws-nova-canvas

📁 If no image save path is specified, the application will automatically create and use the folder above.

Usage Example

Limitations

• Prompt text supports up to 1024 characters
• Image generation allows up to 3 images at a time
• Image variation requires 1-5 reference images
• Color guide supports 1-10 color codes

License

MIT License