MCP Server Amazon Bedrock

🚀 Amazon Bedrock MCP Server

An MCP (Model Control Protocol) server integrating Amazon Bedrock's Nova Canvas model for AI image generation.

✨ Features

• Generate high-quality images from text descriptions using Amazon's Nova Canvas model.
• Achieve advanced control through negative prompts to optimize image composition.
• Enjoy flexible configuration options, supporting custom image sizes and quality.
• Support seed value control to ensure the reproducibility of the generation process.
• Benefit from a robust input validation and error handling mechanism.

🚀 Quick Start

Prerequisites

1. Have a valid AWS account with access to Amazon Bedrock and the Nova Canvas model.
2. Properly configured AWS credentials with the appropriate Bedrock permissions.
3. Node.js version 18 or higher.

📦 Installation

AWS Credential Configuration

The server requires AWS credentials with access to Amazon Bedrock. You can configure them in any of the following ways:

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 chosen region
   

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

   [the_profile_name]
   aws_access_key_id = your_access_key
   aws_secret_access_key = your_secret_key
   

   Set the environment variable to specify the configuration file:

   export AWS_PROFILE=the_profile_name
   

3. IAM role (used when deploying on AWS infrastructure)

Claude Desktop Integration

To integrate the server into 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": "Execution command",
      "args": []
    }
  }
}

💻 Usage Examples

Available Tools - generate_image Function Parameters

Basic Usage

const { generateImage } = require('@your-package');

async function main() {
    const response = await generateImage({
        bucket: 'my-image-bucket',
        objectKey: 'generated-image.png',
        prompt: 'A flying blue bird',
        negativePrompt: 'low quality, blurry',
        width: 800,
        height: 600,
        quality: 100
    });
    
    console.log('Image generation completed');
}

📚 Documentation

Development Guide

Clone the Repository

git clone https://github.com/your-repository.git
cd your-repository

Install Dependencies

npm install

Build the Project

npm run build

Performance Considerations

The image generation time is affected by the resolution, quantity, and quality settings. Please be aware of potential timeout issues in your implementation.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.