Amazon Bedrock Nova Canvas MCP Server

Overview

The Amazon Bedrock Nova Canvas MCP Server allows AI assistants to generate images using Amazon's Nova Canvas model through the Model Context Protocol (MCP). This server acts as a bridge between your AI assistant and Amazon Bedrock's powerful image generation capabilities.

Prerequisites

Before using this MCP server, you'll need:

1. An active AWS account with Amazon Bedrock access
2. Access to the Nova Canvas model in your AWS account
3. AWS credentials with appropriate permissions for Amazon Bedrock
4. Node.js version 18 or later

Installation

Setting Up AWS Credentials

The server requires AWS credentials with Amazon Bedrock permissions. You can configure these using one of these methods:

1. Environment variables:

export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_REGION=us-east-1  # or your preferred region

2. AWS credentials file (~/.aws/credentials):

[your_profile_name]
aws_access_key_id = your_access_key
aws_secret_access_key = your_secret_key

Then set the active profile:

export AWS_PROFILE=your_profile_name

3. IAM role (when deployed on AWS infrastructure)

Integration with Claude Desktop

To integrate with Claude Desktop, add the following configuration to your settings file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "amazon-bedrock": {
      "command": "npx",
      "args": [
        "-y",
        "@zxkane/mcp-server-amazon-bedrock"
      ],
      "env": {
        "AWS_PROFILE": "your_profile_name",         // Optional, only if using a specific profile
        "AWS_ACCESS_KEY_ID": "your_access_key",     // Optional if using AWS credentials file or IAM role
        "AWS_SECRET_ACCESS_KEY": "your_secret_key", // Optional if using AWS credentials file or IAM role
        "AWS_REGION": "us-east-1"                   // Optional, defaults to 'us-east-1'
      }
    }
  }
}

Usage Tips

Prompt Guidelines

For optimal results:

• Avoid negative phrasing ("no", "not", "without") in the main prompt
• Use the negativePrompt parameter for elements you want to exclude
• Be specific and descriptive in your prompts
• Experiment with different cfg_scale values to balance creativity and prompt adherence

Performance Considerations

Image generation time depends on several factors:

• Higher resolution (width and height) increases generation time
• Premium quality takes longer than standard quality
• Generating multiple images increases processing time

Be mindful of these factors when configuring your requests, especially in time-sensitive applications.

Error Handling

The server includes robust error handling for common issues:

• Invalid parameter values
• AWS authentication problems
• Service availability issues

If you encounter errors, check your AWS credentials and ensure you have the necessary permissions for Amazon Bedrock.