Amazon Bedrock
Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images
What is Amazon Bedrock?
Amazon Bedrock is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context procotol(mcp) server for using amazon bedrock nova canvas to generate images
Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Procotol(MCP) server for using Amazon Bedrock
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx amazon-bedrock-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Amazon Bedrock
Amazon Bedrock MCP Server is a Node.js MCP integration that exposes Amazon Bedrock's Nova Canvas image generation model as an MCP tool, enabling AI agents such as Claude to generate images on demand through natural-language prompts. It handles AWS authentication through standard credential chains (environment variables, shared credentials file, or IAM roles) and provides a single generate_image tool with full control over image dimensions, quality, guidance scale, seed, and negative prompts. This server is ideal for workflows that need programmatic image generation embedded directly in AI assistant conversations.
Prerequisites
- Node.js 18+ and npm installed
- An AWS account with Amazon Bedrock access enabled in your target region
- AWS IAM permissions for bedrock:InvokeModel on the Nova Canvas model (amazon.nova-canvas-v1:0)
- AWS credentials configured via environment variables, ~/.aws/credentials, or an IAM role
- An MCP-compatible client such as Claude Desktop
Install the package via npx (recommended)
Use npx to run the server without a global install. This is the recommended approach for Claude Desktop integration.
npx -y @zxkane/mcp-server-amazon-bedrockConfigure AWS credentials
Set up your AWS credentials using environment variables or the AWS credentials file. The server defaults to the us-east-1 region if AWS_REGION is not set.
export AWS_ACCESS_KEY_ID=your-access-key-id
export AWS_SECRET_ACCESS_KEY=your-secret-access-key
export AWS_REGION=us-east-1Enable Nova Canvas in Amazon Bedrock
Log into the AWS Console, navigate to Amazon Bedrock > Model access, and request access to the Amazon Nova Canvas model in your chosen region.
Configure your MCP client
Add the server to your Claude Desktop configuration with your AWS credentials as environment variables.
Generate your first image
Once connected, ask Claude to generate an image. The generate_image tool accepts a prompt, optional negativePrompt, width, height (default 1024px), quality (standard or premium), cfg_scale (1.1–10, default 6.5), seed, and numberOfImages.
Amazon Bedrock Examples
Client configuration
Add the Amazon Bedrock MCP server to Claude Desktop using npx, with 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"
}
}
}
}Prompts to try
Use natural language to generate images through Amazon Bedrock Nova Canvas.
- "Generate an image of a futuristic city skyline at sunset."
- "Create a photorealistic image of a golden retriever in a field of sunflowers, premium quality."
- "Generate a 512x512 image of a serene mountain lake at dawn."
- "Make an image of a coffee cup on a wooden desk, no people, no text in the background."
- "Generate 3 variations of a minimalist logo concept for a tech startup."Troubleshooting Amazon Bedrock
AccessDeniedException when calling InvokeModel
Your IAM user or role does not have permission to invoke the Nova Canvas model. Attach an IAM policy allowing 'bedrock:InvokeModel' on 'arn:aws:bedrock:*::foundation-model/amazon.nova-canvas-v1:0', and confirm model access is enabled in the Bedrock console for your region.
Model not available in selected region
Amazon Nova Canvas availability varies by region. Set AWS_REGION to us-east-1 (N. Virginia) which has the broadest Bedrock model availability, or check the Bedrock documentation for supported regions.
Generated images are not returned or the tool call hangs
Nova Canvas image generation can take 10–30 seconds for high-quality requests. Ensure your MCP client does not have a short tool-call timeout configured. Check that numberOfImages is set to 1 for fastest response during debugging.
Frequently Asked Questions about Amazon Bedrock
What is Amazon Bedrock?
Amazon Bedrock is a Model Context Protocol (MCP) server that model context procotol(mcp) server for using amazon bedrock nova canvas to generate images It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Amazon Bedrock?
Follow the installation instructions on the Amazon Bedrock GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Amazon Bedrock?
Amazon Bedrock works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Amazon Bedrock free to use?
Yes, Amazon Bedrock is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Amazon Bedrock Alternatives — Similar Cloud Services Servers
Looking for alternatives to Amazon Bedrock? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Amazon Bedrock in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Amazon Bedrock?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.