
Imagician
Enables comprehensive image editing operations including resizing, format conversion, cropping, compression, rotation, flipping, and batch processing. Supports JPEG, PNG, WebP, and AVIF formats with quality control and metadata extraction.
README
Imagician - MCP Image Editor
A Model Context Protocol (MCP) server for comprehensive image editing operations including resizing, format conversion, cropping, compression, and more.
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
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。