image-worker

Effortlessly resize, convert, optimize, and transform images with a single MCP server—then upload them directly to S3, Cloudflare R2, or Google Cloud Storage. Ideal for AI workflows, automation scripts, and developers who want seamless image handling in one tool.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio boomlinkai-image-worker-mcp npx -y @boomlinkai/image-worker-mcp \
  --env S3_BUCKET="your-s3-bucket" \
  --env S3_REGION="us-east-1" \
  --env GCLOUD_BUCKET="your-gcp-bucket" \
  --env UPLOAD_SERVICE="s3" \
  --env AWS_ACCESS_KEY_ID="your-aws-access-key-id" \
  --env GCLOUD_PROJECT_ID="your-gcp-project-id" \
  --env CLOUDFLARE_R2_BUCKET="your-r2-bucket" \
  --env AWS_SECRET_ACCESS_KEY="your-aws-secret-access-key" \
  --env CLOUDFLARE_R2_ENDPOINT="https://your-r2-endpoint" \
  --env GCLOUD_CREDENTIALS_PATH="path/to/credentials.json" \
  --env CLOUDFLARE_R2_ACCESS_KEY_ID="your-cloudflare-access-key" \
  --env CLOUDFLARE_R2_SECRET_ACCESS_KEY="your-cloudflare-secret"

How to use

Boomlinkai image-worker-mcp is a lightweight MCP server focused on image processing and cloud uploads. It uses the MCP standard to expose tools for resizing, transforming, and uploading images to supported cloud services such as AWS S3, Cloudflare R2, and Google Cloud Storage. With its stdin/stdout based communication, you can drive it from AI assistants, automation workflows, or code editors by sending tool calls like resize_image and upload_image. The provided examples demonstrate resizing an image and then uploading the result to a cloud provider. To start, run the server via npx, which fetches and runs the MCP package directly. Once running, you can issue commands to resize images (specifying input as a path, URL, or base64) and to upload them to your chosen service, with credentials supplied via environment variables.

How to install

Prerequisites:

Node.js 18.x or higher installed on your machine
Internet access to fetch the MCP package

Installation options:

Global install and run:

npm install -g @boomlinkai/image-worker-mcp
# Then run directly (example)
image-worker-mcp

Run via npx without installing:

npx @boomlinkai/image-worker-mcp

Use yarn or pnpm equivalents:

yarn global add @boomlinkai/image-worker-mcp
# or
pnpm add -g @boomlinkai/image-worker-mcp

Start the server:

npx @boomlinkai/image-worker-mcp

Prerequisites note:

Ensure sharp dependencies install correctly. If you encounter issues on ARM/Apple Silicon, install libvips separately or use Node 18+.

Additional notes

Environment variables are required for cloud uploads. Do not commit credentials to source control. Supported services include AWS S3, Cloudflare R2, and Google Cloud Storage. If you use a different default upload service, override UPLOAD_SERVICE accordingly (e.g., export UPLOAD_SERVICE=gcloud). For debugging, check that input image formats are supported by sharp, and confirm that input sources (URL, path, or base64) are valid. If image outputs appear blank or corrupted, verify input validity and ensure the appropriate environment variables are loaded in the process that runs the MCP server. The MCP server operates over stdio, making it compatible with many automation tools and editors.

Related MCP Servers

docs

1.1k

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

memory-bank

871

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

mcp -azure-devops

339

An MCP server for Azure DevOps

BifrostMCP

205

VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs

Vibe-Coder

Vibe-Coder-MCP server extends AI assistants with specialized software development tools.

mcp-image-extractor

MCP server which allow LLM in agent mode to analyze image whenever it needs