Amazon Bedrock

Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "zxkane-mcp-server-amazon-bedrock": {
      "command": "npx",
      "args": [
        "-y",
        "@zxkane/mcp-server-amazon-bedrock"
      ],
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_PROFILE": "YOUR_PROFILE_NAME",
        "AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY",
        "AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_KEY"
      }
    }
  }
}

You run a specialized MCP server that connects to Amazon Bedrock’s Nova Canvas model to generate AI images from text prompts. It supports fine-grained control through negative prompts, deterministic outputs with seeds, and configurable image dimensions and quality. This server is useful when you want programmatic image generation integrated into your workflows or tools via the MCP protocol.

How to use

To use this MCP server, connect your MCP client to the local process or run it as a stand‑alone service. You can generate images by sending a generate_image request with a prompt and optional controls such as width, height, quality, and seed. You can also steer outputs with a negativePrompt to exclude unwanted elements.

If you are integrating with Claude Desktop, you can configure the client to trigger the MCP server by adding the provided config. This enables seamless cross‑application image generation from your existing Claude workflow.

How to install

Prerequisites you must have before installing the MCP server: Node.js version 18 or later, and an active AWS account with Bedrock access and Nova Canvas permissions.

Prepare AWS credentials. You can provide credentials via environment variables, AWS credentials file, or an IAM role when running on AWS infrastructure.
Install dependencies and build the server locally.

# Install dependencies
npm install

# Build the server (if a build step is provided)
npm run build

Additional notes

Configuration and usage details shown here assume you will run the MCP server locally via a stdio command. The recommended runtime command is shown as part of the MCP setup below.

Environment variables for AWS Bedrock access are described in the integration snippet. You can supply them directly when running the server or configure a profile to simplify repeated runs.

Available tools

generate_image

Creates images from text descriptions using Amazon Bedrock's Nova Canvas model. You can set a prompt, an optional negativePrompt to exclude elements, dimensions, quality, and a seed for deterministic results.

Built by

VeilStrat

AI signals for GTM teams