Amazon Bedrock MCP Server

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

Catalog onlyCatalog onlySTDIO

Overview

Amazon Bedrock MCP Server is a Model Control Protocol (MCP) server that integrates with Amazon Bedrock's Nova Canvas model to generate high-quality images from text descriptions.

To use the MCP Server, configure your AWS credentials and run the server using Node.js. You can then send image generation requests with specific parameters for prompts and configurations.

High-quality image generation from text descriptions. - Advanced control over image composition using negative prompts. - Flexible configuration for image size and quality. - Deterministic image generation using seed control. - Robust error handling and input validation.

Generating images for creative projects based on descriptive text.
Integrating with applications that require automated image generation from user input.
Utilizing the server for marketing content or visualization in reports.

Add to your AI client

Use these steps to connect Amazon Bedrock MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-amazon-bedrock-zxkane": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-amazon-bedrock-zxkane"
      ]
    }
  }
}

FAQ

What prerequisites are needed to run the server?

You need an active AWS account, proper AWS credentials, and Node.js version 18 or later.

How do I configure AWS credentials?

You can configure AWS credentials using environment variables, an AWS credentials file, or an IAM role.

Can the MCP server generate images in bulk?

Yes, you can specify a batch size for generation by setting the numberOfImages parameter when making requests.

Image and video processing

Amazon Bedrock MCP Server — MCP Registry