MCP Catalogs
Home

mcp-server-amazon-bedrock

by zxkane·24·Score 37

MCP server for Amazon Bedrock Nova Canvas AI image generation with configurable parameters.

ai-llmmediadeveloper-tools
12
Forks
0
Open issues
13 mo ago
Last commit
2d ago
Indexed

Overview

This MCP server provides integration with Amazon Bedrock's Nova Canvas model for AI image generation. It offers high-quality image creation from text descriptions with advanced controls including negative prompts, configurable dimensions, quality settings, and deterministic generation through seed control. The server features robust input validation and error handling, making it suitable for production environments where reliable image generation is required.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Content creators needing AI-generated images for blogs, social media, or marketing materials
you:Designers generating concept art or mockups with specific requirements
you:Applications requiring programmatic image generation based on user input
you:What AWS permissions are required for this server?
you:Can I generate images with custom aspect ratios?

When to choose this

Choose this server if you already use AWS services and need high-quality image generation through Amazon Bedrock's Nova Canvas model with MCP integration.

When NOT to choose this

Avoid if you don't want AWS vendor lock-in or if you need image generation services outside of AWS ecosystem.

Tools this server exposes

1 tool extracted from the README
  • generate_image

    Creates images from text descriptions using Amazon Bedrock's Nova Canvas model

Comparable tools

mcp-server-openai-dallemcp-server-stable-diffusionmcp-server-midjourney

Installation

Installation

AWS Credentials Configuration

The server requires AWS credentials with appropriate Amazon Bedrock permissions. Configure these using one of the following 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
  1. AWS credentials file (~/.aws/credentials):
[the_profile_name]
aws_access_key_id = your_access_key
aws_secret_access_key = your_secret_key

Environment variable for active profile:

export AWS_PROFILE=the_profile_name
  1. IAM role (when deployed on AWS infrastructure)

Claude Desktop Integration

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",
        "AWS_ACCESS_KEY_ID": "your_access_key",
        "AWS_SECRET_ACCESS_KEY": "your_secret_key",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

FAQ

What AWS permissions are required for this server?
The server requires permissions to access Amazon Bedrock and the Nova Canvas model. Specifically, it needs the bedrock:InvokeModel permission for the model inference.
Can I generate images with custom aspect ratios?
Yes, the server allows you to specify both width and height parameters independently, enabling any custom aspect ratio for image generation.

Compare mcp-server-amazon-bedrock with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.