Mochify MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
git clone https://github.com/getmochify/mochify-cli
cd mochify-cli

Then follow the repository README for any remaining dependency or build steps before continuing.

2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add mochify-mcp -- node "<FULL_PATH_TO_MOCHIFY_CLI>/dist/index.js"

Replace <FULL_PATH_TO_MOCHIFY_CLI>/dist/index.js with the actual folder you prepared in step 1.

README.md

Fast, privacy-first image compression and conversion API

mochify-cli

A command-line tool and MCP server for mochify.xyz — a fast, privacy-first image compression and conversion API powered by a native C++ engine.

Compress and convert images to modern formats (AVIF, JXL, WebP, Jpegli) from your terminal, or give AI assistants like Claude direct access to image processing via the Model Context Protocol.

Installation

macOS (Homebrew):

brew tap getmochify/mochify
brew install mochify

Linux / WSL:

# x86_64
curl -L https://github.com/getmochify/mochify-cli/releases/latest/download/mochify-linux-x86_64 -o mochify
chmod +x mochify
sudo mv mochify /usr/local/bin/

# arm64
curl -L https://github.com/getmochify/mochify-cli/releases/latest/download/mochify-linux-arm64 -o mochify
chmod +x mochify
sudo mv mochify /usr/local/bin/

Manual: All binaries at Releases.

From source:

cargo install --path .

CLI Usage

mochify [OPTIONS] <FILES>...

Options

Flag Description
-t, --type <FORMAT> Output format: jpg, png, webp, avif, jxl
-w, --width <N> Target width in pixels
-H, --height <N> Target height in pixels
--crop Crop to exact dimensions
-r, --rotation <DEG> Rotation: 0, 90, 180, 270
-o, --output <DIR> Output directory (default: same as input)
-p, --prompt <TEXT> Natural-language prompt — resolves params automatically
-k, --api-key <KEY> API key (or set MOCHIFY_API_KEY env var)

Examples

# Convert a JPEG to AVIF
mochify photo.jpg -t avif

# Resize and convert to WebP
mochify photo.jpg -t webp -w 800

# Batch convert a folder to AVIF at 1200px wide
mochify ./images/*.jpg -t avif -w 1200 -o ./compressed

# With an API key
MOCHIFY_API_KEY=your-key mochify photo.jpg -t jxl

# Use a natural-language prompt instead of explicit flags
mochify photo.jpg -p "convert to avif and resize to 1200px wide"

# Prompt works with multiple files too
mochify ./images/*.jpg -p "compress for web, keep under 1000px wide" -o ./out

Free usage is 25 images per day without an API key. Visit mochify.xyz for more.

MCP Server (Claude Desktop)

mochify can run as an MCP server, letting Claude process images on your behalf directly from conversation.

Setup

Add the following to your Claude Desktop config at ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "mochify": {
      "command": "mochify",
      "args": ["serve"]
    }
  }
}

With an API key (for higher limits):

{
  "mcpServers": {
    "mochify": {
      "command": "mochify",
      "args": ["serve"],
      "env": {
        "MOCHIFY_API_KEY": "your-key-here"
      }
    }
  }
}

Restart Claude Desktop. The mochify server will appear in your connections.

Usage

Just describe what you want in natural language, with the full path to your image:

"Convert /Users/me/Desktop/photo.jpg to AVIF at 1000px wide"

"Compress all the JPEGs in /Users/me/projects/blog/images/ to WebP and save them to /Users/me/projects/blog/compressed/"

Claude will call the squish tool automatically.

API

Powered by the mochify.xyz API at https://api.mochify.xyz/v1/squish.

  • Images are processed in-memory and never stored on disk
  • Supports JPEG (Jpegli), AVIF, JXL, WebP, and PNG output
  • Up to 25MB per image

Visit mochify.xyz for the web interface.

Tools (1)

squishProcesses images in-memory to convert, compress, or resize them based on natural language instructions.

Environment Variables

MOCHIFY_API_KEYAPI key for higher usage limits

Configuration

claude_desktop_config.json
{"mcpServers": {"mochify": {"command": "mochify", "args": ["serve"]}}}

Try it

Convert /Users/me/Desktop/photo.jpg to AVIF at 1000px wide
Compress all the JPEGs in /Users/me/projects/blog/images/ to WebP and save them to /Users/me/projects/blog/compressed/
Resize this image to 800px width and convert it to JXL format
Optimize all images in my project folder to be under 1000px wide for web use

Frequently Asked Questions

What are the key features of Mochify?

Supports modern formats including AVIF, JXL, WebP, Jpegli, and PNG. Processes images in-memory without storing them on disk. Handles up to 25MB per image. Natural language processing for image transformation parameters. Native C++ engine for high-performance compression.

What can I use Mochify for?

Quickly converting high-resolution photography to web-ready formats. Batch compressing project assets to reduce website load times. Resizing images for social media or blog posts directly via Claude. Automating image format standardization for development workflows.

How do I install Mochify?

Install Mochify by running: brew tap getmochify/mochify && brew install mochify

What MCP clients work with Mochify?

Mochify works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Mochify docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare