Mcp Image Optimizer
@piephai
A Model Context Protocol server for image optimization. Process images from URLs or local files with advanced transformations powered by Sharp.
Installation
Install in Claude Code
Run this command to add the MCP server:
claude mcp add image-optimizer -- npx -y mcp-image-optimizer
See Claude Code MCP docs for more info.
Install in Claude Desktop
Add to your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"image-optimizer": {
"command": "npx",
"args": ["mcp-image-optimizer"]
}
}
}
Install in OpenAI Codex
Add the following configuration to your OpenAI Codex MCP server settings:
[mcp_servers.image-optimizer]
args = ["-y", "mcp-image-optimizer"]
command = "npx"
See OpenAI Codex for more information.
Install in VSCode
Add to your VS Code settings for MCP extensions like Cline or Continue:
{
"image-optimizer": {
"command": "npx",
"args": ["mcp-image-optimizer"]
}
}
Install in Cursor
Navigate to Settings → Cursor Settings → MCP → Add new global MCP server
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"image-optimizer": {
"command": "npx",
"args": ["mcp-image-optimizer"]
}
}
}
Alternative: Global Install
Install globally for faster startup:
npm install -g mcp-image-optimizer
Then use this simpler config in any client:
{
"command": "mcp-image-optimizer"
}
Usage Examples
Ask your AI assistant:
- "Optimize ~/Desktop/photo.jpg to 800px width"
- "Convert https://images.pexels.com/photos/32206277/pexels-photo-32206277.jpeg to WebP"
- "Batch optimize all images in ~/Downloads/"
- "Create a 200x200 thumbnail with smart crop"
- "Generate a placeholder for lazy loading"
- "Add my company logo as watermark to product images"
- "Add 'Copyright 2025' text watermark"
- "Generate all favicon sizes from my logo"
Available Tools
optimize_image
Resize, convert, and transform images.
Example:
"Optimize image.jpg to 800px width with 85% quality"
Parameters:
input- Image path or URLoutput- Output file pathwidth- Target width in pixelsheight- Target height in pixelsquality- Quality 1-100 for lossy formatsformat- Output format (jpeg, png, webp, avif, tiff)fit- Resize fit mode (cover, contain, fill, inside, outside)- Plus rotate, flip, grayscale, blur, sharpen, normalize
batch_optimize
Process multiple images at once.
Example:
"Optimize all images in ~/Pictures/ to 1200px width"
Parameters:
inputs- Array of image paths or URLsoutputDir- Output directorywidth,height,quality,format- Same as single imageprefix- Add to filename startsuffix- Add to filename end
get_image_info
Extract image metadata.
Example:
"Get info about image.jpg"
Returns:
- Dimensions, format, color space
- File size, DPI
- EXIF data presence
auto_crop
Remove borders and whitespace automatically.
Example:
"Auto-crop screenshot.png to remove white borders"
Parameters:
input- Image path or URLoutput- Output file paththreshold- Color similarity threshold 0-100backgroundColor- Background to detect
smart_crop
Intelligent cropping to specific dimensions.
Example:
"Smart crop portrait.jpg to 500x500 square"
Parameters:
input- Image path or URLoutput- Output file pathwidth,height- Target dimensionsstrategy- "attention" or "entropy"
create_placeholder
Generate low-quality image placeholders for lazy loading.
Example:
"Create a blurred placeholder for hero-image.jpg"
Parameters:
input- Image path or URLwidth- Placeholder width (default: 20)height- Placeholder height (auto if not set)quality- JPEG quality 1-100 (default: 40)blur- Blur amount 0.3-1000 (default: 5)format- "base64", "datauri", or "file"
add_watermark
Add image or text watermarks with positioning and styling.
Example:
"Add logo.png as watermark to photo.jpg in bottom-right corner"
"Add 'Copyright 2025' text watermark with 50% opacity"
"Add 'CONFIDENTIAL' diagonally across the document"
Parameters:
input- Image path or URLoutput- Output file pathwatermark- Path/URL to watermark image, base64 data, or textposition- Corner, center, diagonal, or tile patternopacity- Transparency 0-1scale- Size relative to base imagemargin- Distance from edgesblend- Blend mode for effects- Text options:
text,fontSize,fontColor,fontFamily
generate_favicon
Generate all favicon sizes and formats for modern web apps.
Example:
"Generate favicons from logo.png and save to ./public"
"Create all icon sizes for my PWA"
Parameters:
input- Source image (recommend 512x512 or larger)outputDir- Directory to save all favicon filessizes- Custom sizes array (default: all standard sizes)platforms- Target platforms: web, apple, android, microsoft, allgenerateManifest- Create manifest.json snippet for PWAs
Generated files:
- PNG favicons in all sizes (16x16 to 512x512)
- apple-touch-icon.png (180x180)
- android-chrome-192x192.png, android-chrome-512x512.png
- mstile-150x150.png (Microsoft tile)
- favicon-html.txt (ready-to-use HTML tags)
- manifest-icons.json (PWA configuration)
Path Support
- ✅ URLs:
https://example.com/image.jpg - ✅ Absolute paths:
/Users/name/Desktop/image.jpg - ✅ Home directory:
~/Desktop/image.jpg - ⚠️ Relative paths: Works with
cwdconfig setting
To use relative paths, add a working directory:
{
"command": "npx",
"args": ["mcp-image-optimizer"],
"cwd": "/Users/yourname/Desktop"
}
Requirements
- Node.js 22+ (npx handles this automatically)
- Compatible MCP client
Troubleshooting
"Command not found"
- Make sure Node.js is installed:
node --version - Try the global install method
"File not found"
- Use absolute paths:
/Users/name/Desktop/image.jpg - Check file permissions
"MCP tools not available"
- Restart your MCP client after configuration
- Check config file is valid JSON
License
MIT