Overview
Amazon Bedrock MCP Server is a Model Control Protocol (MCP) server that integrates with Amazon Bedrock's Nova Canvas model for AI image generation, allowing users to create high-quality images from text descriptions.
To use the server, you need to configure your AWS credentials, install the necessary dependencies, and then call the generate_image tool with the appropriate parameters to create images based on your text prompts.
- High-quality image generation from text descriptions using Amazon's Nova Canvas model - Advanced control through negative prompts to refine image composition - Flexible configuration options for image dimensions and quality - Deterministic image generation with seed control - Robust input validation and error handling
- Generating artistic images for creative projects
- Creating visual content for marketing and advertising
- Developing prototypes for applications that require image generation
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": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}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": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"zxkane-mcp-server-amazon-bedrock-mcp-mirror": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-zxkane-mcp-server-amazon-bedrock-mcp-mirror"
]
}
}
}FAQ
What are the prerequisites to use the server?
You need an active AWS account with access to Amazon Bedrock, properly configured 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 when deployed on AWS infrastructure.
Can I control the quality of the generated images?
Yes! You can specify the image quality level as either "standard" or "premium" when generating images.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1152,"uuid":"6e956713-dd92-483f-ac6c-e73b6d704910","name":"zxkane_mcp-server-amazon-bedrock","title":"Amazon Bedrock MCP Server","description":"Mirror of","avatar_url":"https://avatars.githubusercontent.com/u/192820360?v=4","created_at":"2025-01-28T02:35:03.825Z","updated_at":"2025-02-23T07:20:08.155Z","status":"created","author_name":"MCP-Mirror","author_avatar_url":"https://avatars.githubusercontent.com/u/192820360?v=4","tags":"amazon-bedrock,mcp-server,ai-image-generation","category":"developer-tools","is_featured":false,"sort":1,"url":"https://github.com/MCP-Mirror/zxkane_mcp-server-amazon-bedrock","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/d2f78ad6e66fa7d593afdadb5e6bfd79482ca6e616d94ec8f4c44b922be168f7/68747470733a2f2f676c616d612e61692f6d63702f736572766572732f39717737647770766a392f6261646765","type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]