Amazon Bedrock

In the AWS Management Console, navigate to Amazon Bedrock, go to Model Access, and request access to the Amazon Nova Canvas model. Access is typically granted immediately but may take a few minutes.

Ensure your AWS credentials are available. The server supports three methods: environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION), an AWS credentials file with a profile, or an IAM role when running on AWS infrastructure.

export AWS_ACCESS_KEY_ID="your-access-key-id"
export AWS_SECRET_ACCESS_KEY="your-secret-access-key"
export AWS_REGION="us-east-1"

Use npx to run the published package directly without a manual build step. Add it to your MCP client configuration with your AWS credentials passed as environment variables.

{
  "mcpServers": {
    "amazon-bedrock": {
      "command": "npx",
      "args": ["-y", "@zxkane/mcp-server-amazon-bedrock"],
      "env": {
        "AWS_ACCESS_KEY_ID": "your-access-key-id",
        "AWS_SECRET_ACCESS_KEY": "your-secret-access-key",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

If you need to customize the server, clone the repository, install dependencies, and build the TypeScript source.

git clone https://github.com/zxkane/mcp-server-amazon-bedrock.git
cd mcp-server-amazon-bedrock
npm install
npm run build

The server exposes a single tool: generate_image. Key parameters include prompt (required, up to 1024 characters), negativePrompt (optional), width and height (default 1024px each), quality ('standard' or 'premium'), cfg_scale (1.1-10, default 6.5), seed (for reproducibility), and numberOfImages (1-5 for batch generation).