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.
3 points
8.7K

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 control
Allows users to control the operations of Photoshop and Premiere Pro through simple natural language instructions.
Multi - platform support
Compatible with multiple AI assistants, including the Claude desktop version, and supports both Mac and Windows systems.
Flexible expansion
New API interfaces can be easily added to support more functions of Adobe tools.
Real - time feedback
Can obtain the status information of Adobe applications to help AI verify whether its operations are successful.
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 photo
Users 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 effect
Users can let AI create a double - exposure effect in Photoshop, blending two pictures together.
Add a transition effect
Users can instruct AI to add a cross - fade effect to all clips in Premiere Pro.

Frequently Asked Questions

What software does the MCP server require?
Can the MCP server automatically obtain images?
How to solve the problem that the plugin cannot connect?
Does the MCP server support other AI assistants?

Related Resources

MCP Server Documentation
The official GitHub repository, containing complete code and documentation.
Video Examples
Video tutorials demonstrating the actual use of the MCP server.
Discord Community
An online community for user communication and problem - solving.
Claude MCP Server
Additional file system access function for loading and embedding images.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
4.5K
4.5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
5.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.3K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
7.5K
5 points
R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.4K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
10.8K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
11.5K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
71.9K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.1K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.6K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase