Amazon Bedrock MCP Server
@zxkane
Model Context Procotol(MCP) server for using Amazon Bedrock Nova Canvas to generate images
概要
What is Amazon Bedrock MCP Server?
A Model Context Protocol (MCP) server that integrates with Amazon Bedrock’s Nova Canvas model to generate high-quality images from text descriptions. It is intended for developers building AI‑powered image generation workflows via MCP‑compatible clients like Claude Desktop.
How to use Amazon Bedrock MCP Server?
Install via npx or clone the repository, configure AWS credentials (environment variables, credentials file, or IAM role), and set up the server in your MCP client’s configuration file. The server exposes a single tool generate_image which accepts parameters such as prompt, negativePrompt, width, height, quality, cfg_scale, seed, and numberOfImages.
Key features of Amazon Bedrock MCP Server
- Text‑to‑image generation using Amazon’s Nova Canvas model
- Negative prompts to exclude unwanted elements
- Configurable image dimensions and quality (standard/premium)
- Deterministic output via seed control
- Batch generation of 1–5 images per call
- Input validation and error handling
Use cases of Amazon Bedrock MCP Server
- Generate marketing visuals from textual descriptions
- Create concept art or storyboard frames with precise composition control
- Iterate on image designs by adjusting prompts, negative prompts, and seed values
- Automate bulk image creation in CI/CD or content‑generation pipelines
FAQ from Amazon Bedrock MCP Server
What does the server do?
It generates images using Amazon Bedrock’s Nova Canvas model based on a text prompt and optional parameters like negative prompt, dimensions, quality, and seed.
What are the runtime requirements?
An active AWS account with Amazon Bedrock and Nova Canvas model access, properly configured AWS credentials, and Node.js 18 or later.
Where are generated images stored?
The README does not specify storage details; images are returned directly via the MCP tool response. No local or cloud persistence is mentioned.
Are there known performance limits?
Generation time increases with higher resolution (width, height), number of images, and quality level. Developers should account for potential timeout implications when using higher values.
How is authentication handled?
AWS credentials must be configured via environment variables, the AWS credentials file, or an IAM role (when deployed on AWS infrastructure). The server does not implement additional authentication.
