ADB - MCP: AI Agent Dev Server for Adobe Tools via MCP & NLP

Adb MCP

adb - mcp is a proof - of - concept project aiming to provide an interface for LLMs through the MCP protocol to create an AI agent for controlling Adobe tools (such as Photoshop and Premiere). This project includes the MCP server, Node command proxy server, and Adobe application plugins, supporting natural language instruction operations on Adobe software and suitable for image and video editing automation.

Image and video processing Developer tools #AI Agent #Adobe Control #Image Editing #Video Editing .JavaScript

rating : 3 points

downloads : 0

update time : 2025-07-23

What is the MCP server?

The MCP server is an intermediate - layer software that provides an interface for AI assistants (such as Claude) to interact with applications like Adobe Photoshop and Premiere Pro. Through the MCP protocol, users can control these professional design tools with natural language instructions.

How to use the MCP server?

The MCP server needs to work together with the Node.js proxy server and Adobe plugins. First, install and configure the Python environment to run the MCP server. Then, start the Node.js proxy service. Finally, load the plugin in the Adobe application. In this way, AI can operate Adobe tools through natural language.

Applicable scenarios

Suitable for users who want to control design tools with natural language, such as quickly creating images, producing video projects, or generating tutorials. It is especially suitable for beginners or designers who want to improve work efficiency.

Main Features

Natural language controlAllows users to control the operations of Photoshop and Premiere Pro through simple natural language instructions.

Multi - platform supportCompatible with multiple AI assistants, including the Claude desktop version, and supports both Mac and Windows systems.

Flexible expansionNew API interfaces can be easily added to support more functions of Adobe tools.

Real - time feedbackCan obtain the status information of Adobe applications to help AI verify whether its operations are successful.

Advantages and Limitations

Advantages

Lower the learning threshold of design tools, enabling non - technical personnel to operate easily.

Improve design efficiency and reduce manual operation time.

Support multiple AI assistants and have good compatibility.

Provide an intuitive interface and detailed documentation support.

Limitations

Currently does not support automatically obtaining image content from Adobe applications.

Some advanced functions have not been fully implemented.

Requires certain technical settings to run properly.

Highly dependent on the Adobe plugin API.

How to Use

Install dependencies

Ensure that Python 3, Node.js, and Adobe UXP developer tools are installed.

Start the MCP server

Enter the mcp directory and run the following commands to start the MCP server: $ cd mcp $ uv run mcp dev ps - mcp.py (for Photoshop) $ uv run mcp dev pr - mcp.py (for Premiere)

Start the proxy server

Enter the adb - proxy - socket directory and run the following commands to start the proxy server: $ cd adb - proxy - socket $ npm install $ node proxy.js

Install Adobe plugins

Enable developer mode in the Adobe application and load the plugin through the UXP developer tools.

Connect to the AI assistant

Click the “Attach from MCP” button in the Claude desktop and select the configuration file for Adobe Photoshop or Premiere.

Usage Examples

Create an Instagram photoUsers can use natural language instructions to let AI create photos in the Instagram style, such as setting appropriate sizes, colors, and effects.

Create a double - exposure effectUsers can let AI create a double - exposure effect in Photoshop, blending two pictures together.

Add a transition effectUsers can instruct AI to add a cross - fade effect to all clips in Premiere Pro.