Amazon Bedrock Nova MCP server

This MCP server enables the creation of images using Amazon Nova Canvas and videos using Amazon Nova Reel models through the Model Context Protocol (MCP) over SSE. It can be integrated with MCP clients like Claude Desktop or LibreChat to enhance your AI assistant's capabilities.

Prerequisites

Before installing the MCP server, ensure you have:

• An Amazon Bedrock account with access to Amazon Nova Canvas and Amazon Nova Reel models
• An Amazon S3 bucket configured to store video content
• An MCP client (Claude Desktop or LibreChat)

Installation

The easiest way to run the MCP server is using Docker with the precompiled image.

Using Docker Compose

1. Create a docker-compose.yml file with the following configuration:

version: '3'
services:
  mcp-server:
    image: [image-name]  # Replace with the actual image name
    ports:
      - "8961:8961"
    environment:
      # Add your environment variables here
      # AWS credentials and configuration

2. Start the container:

docker-compose up -d

The MCP server will be accessible at http://localhost:8961.

Integration with LibreChat

Configuration

To add the MCP server to LibreChat:

1. Open your librechat.yaml configuration file
2. Add the following section to the file:

mcpServers:
  media-creator:
    type: sse # type can optionally be omitted
    url: http://localhost:8961/sse  # Replace with your actual server URL

3. Save the file and restart LibreChat

Usage in LibreChat

After adding the MCP server to LibreChat:

1. Restart LibreChat to connect to the MCP server and discover the available tools
2. Create a new agent in LibreChat
3. Add the image creation and/or video creation tools to your agent
4. Start a conversation with your agent
5. Request the agent to create an image or video

Examples of prompts you can use:

• "Create an image of a mountain landscape at sunset"
• "Generate a short video of ocean waves crashing on a beach"

The agent will invoke the appropriate tool (Nova Canvas for images or Nova Reel for videos) through the MCP server.

Verifying Operation

You can verify the server is running correctly by:

• Checking the Docker container logs for any errors
• Confirming the server is accessible at http://localhost:8961
• Testing a simple image or video generation request through your MCP client

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.