AWS Nova Canvas MCP server for AI agents

Amazon Nova Canvas MCP Server provides an interface for generating images using Amazon Nova Canvas through the Model Context Protocol (MCP). It offers text-based and color-guided image generation with various customization options, saving results directly to your workspace.

Prerequisites

Before installing the MCP server, ensure you have:

Installed uv from Astral or GitHub
Installed Python 3.10 using uv python install 3.10
Set up AWS credentials with access to Amazon Bedrock and Nova Canvas:
- An AWS account with Amazon Bedrock and Amazon Nova Canvas enabled
- AWS credentials configured with aws configure or environment variables
- IAM role/user with permissions for Amazon Bedrock and Nova Canvas

Installation

Standard Installation

Configure the MCP server in your MCP client configuration (e.g., for Amazon Q Developer CLI, edit ~/.aws/amazonq/mcp.json):

{
  "mcpServers": {
    "awslabs.nova-canvas-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.nova-canvas-mcp-server@latest"],
      "env": {
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1",
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Docker Installation

After building with docker build -t awslabs/nova-canvas-mcp-server ., create a .env file with AWS credentials:

AWS_ACCESS_KEY_ID=ASIAIOSFODNN7EXAMPLE
AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
AWS_SESSION_TOKEN=AQoEXAMPLEH4aoAH0gNCAPy...truncated...zrkuWJOgQs8IZZaIv2BXIa2R4Olgk

Then configure your MCP client:

{
  "mcpServers": {
    "awslabs.nova-canvas-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env",
        "AWS_REGION=us-east-1",
        "--env",
        "FASTMCP_LOG_LEVEL=ERROR",
        "--env-file",
        "/full/path/to/file/above/.env",
        "awslabs/nova-canvas-mcp-server:latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Note: Your credentials will need to be kept refreshed from your host.

Installing via Smithery

For Claude Desktop users, you can install automatically via Smithery:

npx -y @smithery/cli install @awslabs/nova-canvas-mcp-server --client claude

AWS Authentication

The 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.

"env": {
  "AWS_PROFILE": "your-aws-profile",
  "AWS_REGION": "us-east-1"
}

Ensure your AWS profile has the necessary permissions for Amazon Bedrock and Amazon Nova Canvas.

Usage

Text-based Image Generation

Use generate_image to create images from text prompts with these options:

Customizable dimensions (320-4096px)
Quality options and negative prompting
Multiple image generation (1-5) in a single request
Adjustable parameters like cfg_scale (1.1-10.0)
Seeded generation for reproducible results

Color-guided Image Generation

Use generate_image_with_colors to generate images with specific color palettes:

Define up to 10 hex color values to influence the image style
Same customization options as text-based generation

Workspace Integration

All generated images are automatically saved to user-specified workspace directories with automatic folder creation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "awslabs-nova-canvas-mcp-server" '{"command":"uvx","args":["awslabs.nova-canvas-mcp-server@latest"],"env":{"AWS_PROFILE":"your-aws-profile","AWS_REGION":"us-east-1","FASTMCP_LOG_LEVEL":"ERROR"},"disabled":false,"autoApprove":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "awslabs.nova-canvas-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.nova-canvas-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "awslabs.nova-canvas-mcp-server": {
            "command": "uvx",
            "args": [
                "awslabs.nova-canvas-mcp-server@latest"
            ],
            "env": {
                "AWS_PROFILE": "your-aws-profile",
                "AWS_REGION": "us-east-1",
                "FASTMCP_LOG_LEVEL": "ERROR"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect