
mcp_adobe_premiere
一个通过 MCP 服务器和 UXP 插件让 LLM 控制 Adobe Premiere Pro 的系统。
Repository Info
About This Server
一个通过 MCP 服务器和 UXP 插件让 LLM 控制 Adobe Premiere Pro 的系统。
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
Adobe Premiere Pro MCP Server
⚠️ DEVELOPMENT NOTICE: This project is currently in active development and is not ready for production use. Features may change without notice, and there are no guarantees about stability or functionality. Use at your own risk.
A system that allows LLMs (like Claude) to control Adobe Premiere Pro through an MCP server and UXP plugin.
Project Overview
Purpose: Implement an MCP server that enables LLMs (Claude, etc.) to control Adobe Premiere Pro
System Requirements
- Adobe Premiere Pro Beta (25.3) or later
- UXP Developer Tool for loading plugins
System Architecture
LLM (Claude Desktop) → MCPServer (Python/fastmcp) → UXP Plugin (TypeScript) → Adobe Premiere Pro
Key Features
- Sequence creation/deletion
- Media file importing
Project Structure
mcp_adobe_premiere
├── LICENSE # Mozilla Public License
├── README.md # Project documentation
├── plugin/ # Adobe UXP Plugin
│ ├── index.html # Plugin UI
│ ├── manifest.json # Plugin manifest
│ ├── package.json # Node.js dependencies
│ ├── tsconfig.json # TypeScript configuration
│ ├── types.d.ts # Adobe Premiere Pro API type definitions
│ ├── webpack.config.js # Webpack configuration
│ └── src/ # Plugin source code
│ ├── index.ts # Plugin entry point
│ ├── tools.ts # API implementation
│ └── websocket_server.ts # WebSocket client for server communication
└── server/ # Python MCP server
├── main.py # Server entry point
├── requirements.txt # Python dependencies
├── tools.py # Tools implementation
├── websocket_server.py # WebSocket server for plugin communication
└── tools/ # Additional tools
└── manage_project.py # Project management tools
Setup Instructions
Server Setup
-
Create and activate a virtual environment:
python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate -
Install dependencies:
pip install -r server/requirements.txt
Claude Desktop Configuration
To enable Claude to control Adobe Premiere Pro, you need to configure Claude Desktop with the MCP server settings:
-
Locate Claude Desktop's configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
-
Add the Adobe Premiere MCP server configuration to the file:
{ "mcpServers": { "adobe-premiere": { "command": "<path-to-virtual- python-executable>", "args": [ "<path-to-server-main.py>" ] } } } -
Example configuration (Windows):
{ "mcpServers": { "adobe-premiere": { "command": "C:\\Users\\username\\Documents\\repos\\mcp_adobe_premiere\\.venv\\Scripts\\python.exe", "args": [ "C:\\Users\\username\\Documents\\repos\\mcp_adobe_premiere\\server\\main.py" ] } } } -
Restart Claude Desktop for the changes to take effect.
Premiere Plugin Setup
-
Install dependencies:
cd plugin npm install -
Build the plugin:
npm run build -
Install UXP Developer Tool and load the plugin in Adobe Premiere Pro:
- Open Adobe Premiere Pro Beta (v25.3 or later)
- Launch UXP Developer Tool
- Click "Add Plugin" and select the folder
pluginfrom this repository - Click "Load" to load the plugin into Premiere Pro
- The plugin should appear as "MCPAdobe" in the Premiere Pro Extensions menu
- Open the plugin panel from Window > Extensions > MCPAdobe
- Connect to the MCP server using the default URL or customize as needed
References
- Adobe UXP Documentation
Quick Start
Clone the repository
git clone https://github.com/morim3/mcp_adobe_premiereInstall dependencies
cd mcp_adobe_premiere
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.