AWS Nova Canvas MCP Server enables AI-powered image generation with comprehensive customization options:
• Text-based generation: Create images from text prompts using the generate_image
tool
• Color-guided generation: Generate images with specific color palettes using the generate_image_with_colors
tool (supports up to 10 hex color values)
• Flexible parameters: Customize dimensions (320-4096 pixels), quality (standard/premium), cfg_scale for prompt adherence, negative prompts to exclude elements, and reproducible seeds
• Batch generation: Create 1-5 images per request
• Workspace integration: Automatically save images to specified directories with folder creation
• Secure access: AWS profile-based authentication for Amazon Bedrock and Nova Canvas services
Amazon Nova Canvas MCP Server
MCP server for generating images using Amazon Nova Canvas
Features
Text-based image generation
Create images from text prompts with
generate_image
Customizable dimensions (320-4096px), quality options, and negative prompting
Supports multiple image generation (1-5) in single request
Adjustable parameters like cfg_scale (1.1-10.0) and seeded generation
Color-guided image generation
Generate images with specific color palettes using
generate_image_with_colors
Define up to 10 hex color values to influence the image style and mood
Same customization options as text-based generation
Workspace integration
Images saved to user-specified workspace directories with automatic folder creation
AWS authentication
Uses AWS profiles for secure access to Amazon Nova Canvas services
Prerequisites
Install
uv
from Astral or the GitHub READMEInstall Python using
uv python install 3.10
Set up AWS credentials with access to Amazon Bedrock and Nova Canvas
You need an AWS account with Amazon Bedrock and Amazon Nova Canvas enabled
Configure AWS credentials with
aws configure
or environment variablesEnsure your IAM role/user has permissions to use Amazon Bedrock and Nova Canvas
Installation
Here are some ways you can work with MCP across AWS, and we'll be adding support to more products including Amazon Q Developer CLI soon: (e.g. for Amazon Q Developer CLI MCP, ~/.aws/amazonq/mcp.json
):
or docker after a succesful docker build -t awslabs/nova-canvas-mcp-server .
:
NOTE: Your credentials will need to be kept refreshed from your host
Installing via Smithery
To install Amazon Nova Canvas MCP Server for Claude Desktop automatically via Smithery:
AWS Authentication
The MCP server uses the AWS profile specified in the AWS_PROFILE
environment variable. If not provided, it defaults to the "default" profile in your AWS configuration file.
Make sure the AWS profile has permissions to access Amazon Bedrock and Amazon Nova Canvas. The MCP server creates a boto3 session using the specified profile to authenticate with AWS services. Your AWS IAM credentials remain on your local machine and are strictly used for using the Amazon Bedrock model APIs.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Provides image generation capabilities using Amazon Nova Canvas through Amazon Bedrock, enabling the creation of visuals from text prompts and color palettes—perfect for mockups, diagrams, and UI design concepts.
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityProvides access to Amazon Bedrock's Nova Canvas model for AI image generation.Last updated -1221MIT License
- -securityFlicense-qualityA Model Context Protocol server that enables AI assistants to create images and videos using Amazon Nova Canvas and Nova Reel models.Last updated -3
- AsecurityAlicenseAqualityAn MCP server that allows you to generate and edit images using Amazon Bedrock's Nova Canvas model, supporting features like text-to-image generation, inpainting, outpainting, image variation, and background removal.Last updated -84MIT License
- -securityAlicense-qualityAn MCP server for generating videos through Amazon Nova Reel 1.1 using AWS Bedrock, providing asynchronous video generation with comprehensive prompting guidelines and multiple transport methods.Last updated -1MIT License