Server & API/Model Context Protocol (MCP)
Docs/Server & API/Model Context Protocol (MCP)
Model Context Protocol (MCP)
Connect Imagerry to Claude Desktop, Cursor, and Zed AI assistants.
The imagerry mcp command exposes image styling tools and presets to AI assistants using the open Model Context Protocol (MCP).
Start the MCP Server
|bash
imagerry mcpSupported Tools & Capabilities
The Imagerry MCP server provides 4 specialized tools for LLM agent workflows:
- 01
customize_image: Applies custom styles, presets, gradients, padding, and formatting directly to local image files on the user's computer.
inputPath(string, required): Absolute file path to the input image.outputPath(string, required): Absolute file path to save the styled output image.preset(string, optional): Built-in preset (default,mesh,gradient,cyberpunk,sunset,studio,aurora) or raw JSON string.format(enum:'png' | 'jpeg' | 'webp', optional): Target output image encoding.quality(number: 1-100, optional): Compression quality for WebP and JPEG.padding(number: 0-100, optional): Canvas padding in percent.borderRadius(number: 0-100, optional): Inner image corner radius.shadowSize(number: 0-100, optional): Drop shadow strength.bgColor(string, optional): Solid background hex code (e.g.#111827).canvasRatio(enum:'auto' | '16:9' | '1:1' | '4:3' | '3:2' | '2:1' | '9:16', optional): Aspect ratio.watermarkText(string, optional): Watermark text overlay.
- 01
batch_customize_images: Batch processes an entire directory of images with parallel processing and live progress reporting.
inputDir(string, required): Absolute path to directory containing images.outputDir(string, required): Absolute path to output directory.preset(string, optional): Preset name to apply to all images.format(enum:'png' | 'jpeg' | 'webp', optional): Target format.quality(number: 1-100, optional): Compression quality.padding(number: 0-100, optional): Padding override.borderRadius(number: 0-100, optional): Radius override.
- 01
list_presets: Lists all available built-in styling presets with names and visual descriptions.
- 01
get_preset_template: Returns the full default JSON configuration schema for building custom presets programmatically.
Claude Desktop Setup
Add the following entry to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
|json
{
"mcpServers": {
"imagerry": {
"command": "imagerry",
"args": ["mcp"],
"env": {
"IMAGERRY_LICENSE_KEY": "YOUR_PRO_LICENSE_KEY"
}
}
}
}Cursor IDE Setup
In Cursor Settings, Features, MCP Servers, Add New Server:
- Name:
imagerry - Type:
command - Command:
imagerry mcp - Environment Variables:
IMAGERRY_LICENSE_KEY=YOUR_KEY
Note
Clean stdio Protocol
Imagerry MCP strictly adheres to JSON-RPC stdio protocol standards. All logs and diagnostics are directed to stderr, ensuring reliable, error-free communication with AI clients.
Found an issue or typo? Report on GitHub
Imagerry CLI Docs • v1.0.0