mcpField
I
Imagician

Imagician

Local
github.com/flowy11Media & Design19Updated 50w ago

About Imagician

Imagician is an MCP server for image editing, covering resizing, format conversion, cropping and compression. It is aimed at users who want an AI assistant to process images directly, and it can be installed from npm and connected to Claude Code, Cursor or Claude Desktop.

Key features

  1. 01Resize images with multiple fit options
  2. 02Convert between JPEG, PNG, WebP and AVIF
  3. 03Crop regions with quality-controlled compression
  4. 04Rotate and flip images
  5. 05Extract image metadata and properties
  6. 06Generate multiple sizes from one image

Use cases

  1. 01Generating responsive image sizes for web pages
  2. 02Converting images in bulk to WebP or AVIF
  3. 03Reducing image file size with compression

MCP support

This project is an MCP server that exposes tools such as resize_image, convert_format, crop_image, compress_image, rotate_image, flip_image, get_image_info and batch_resize to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"imagician": {
"command": "npx",
"args": [
"-y",
"@flowy11/imagician"
]
}
}
}
Run commandnpx -y @flowy11/imagician

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@flowy11/imagician

Tools

8

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
inputPathstringYesPath to input image
outputPathstringYesPath to save resized image
widthnumberNoTarget width in pixels
heightnumberNoTarget height in pixels
fitenumNoHow the image should be resized to fitcover | contain | fill | inside | outside
preserveAspectRatiobooleanNoMaintain original aspect ratio

Details

From the project README

Imagician - MCP Image Editor

npm version

A Model Context Protocol (MCP) server for comprehensive image editing operations including resizing, format conversion, cropping, compression, and more.

Imagician MCP server

Features

  • Resize: Change image dimensions with various fit options
  • Format Conversion: Convert between JPEG, PNG, WebP, and AVIF
  • Crop: Extract specific regions from images
  • Compress: Reduce file size with quality control
  • Rotate: Rotate images by any angle
  • Flip: Mirror images horizontally or vertically
  • Batch Processing: Generate multiple sizes from a single image
  • Metadata: Extract image information and properties

Installation

From npm
npm install -g @flowy11/imagician
From source
git clone https://github.com/flowy11/imagician.git
cd imagician
npm install
npm run build

Usage with Claude Code

Add to your Claude Code configuration (~/.config/claude/config/settings/mcp-servers.json):

{
  "imagician": {
    "command": "npx",
    "args": ["-y", "@flowy11/imagician"]
  }
}

Usage with Cursor

Add to your Cursor configuration (~/.cursor/mcp_settings.json):

{
  "mcpServers": {
    "imagician": {
      "command": "npx",
      "args": ["-y", "@flowy11/imagician"]
    }
  }
}

Usage with Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

Quick setup with npx (recommended):
{
  "mcpServers": {
    "imagician": {
      "command": "npx",
      "args": ["-y", "@flowy11/imagician"]
    }
  }
}
If installed globally via npm:
{
  "mcpServers": {
    "imagician": {
      "command": "imagician"
    }
  }
}
If installed from source:
{
  "mcpServers": {
    "imagician": {
      "command": "node",
      "args": ["/path/to/imagician/dist/index.js"]
    }
  }
}

Available Tools

resize_image

Resize an image to specified dimensions with various fit options.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save resized image
- width: Target width in pixels (optional)
- height: Target height in pixels (optional)
- fit: How to resize (cover, contain, fill, inside, outside)
- preserveAspectRatio: Maintain aspect ratio (default: true)
convert_format

Convert between image formats with quality control.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save converted image
- format: Target format (jpeg, png, webp, avif)
- quality: Quality for lossy formats (1-100, default: 80)
crop_image

Extract a specific region from an image.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save cropped image
- left: Left offset in pixels
- top: Top offset in pixels
- width: Width of crop area
- height: Height of crop area
compress_image

Reduce image file size with quality settings.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save compressed image
- quality: Compression quality (1-100, default: 80)
- progressive: Use progressive encoding for JPEG (default: true)
rotate_image

Rotate an image by any angle.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save rotated image
- angle: Rotation angle in degrees (positive = clockwise)
- background: Background color for exposed areas (default: #000000)
flip_image

Mirror an image horizontally or vertically.

Parameters:
- inputPath: Path to input image
- outputPath: Path to save flipped image
- direction: Flip direction (horizontal, vertical, both)
get_image_info

Extract metadata and information about an image.

Parameters:
- inputPath: Path to image file

Returns: format, dimensions, color space, file size, etc.
batch_resize

Generate multiple sizes from one image (perfect for responsive images).

Parameters:
- inputPath: Path to input image
- outputDir: Directory to save resized images
- sizes: Array of {width, height?, suffix}
- format: Output format for all sizes (optional)

Example Usage in Claude

"Please resize image.jpg to 800x600 pixels"
"Convert photo.png to WebP format with 90% quality"
"Crop avatar.jpg starting at (100, 100) with 200x200 size"
"Generate thumbnail sizes: 150px, 300px, and 600px wide"

Development

# Install dependencies
npm install

# Build TypeScript
npm run build

# Run in development mode
npm run dev

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.