Note: This is a temporary fork for a bug fix PR. See the original at leancoderkavy/premiere-pro-mcp.

Premiere Pro MCP Server

Give AI full control over Adobe Premiere Pro.

269 tools across 28 modules — the most comprehensive MCP server for video editing.

What is this?

An MCP (Model Context Protocol) server that lets AI assistants like Claude, Windsurf, Cursor, or any MCP-compatible client directly control Adobe Premiere Pro — importing media, editing timelines, applying effects, managing keyframes, exporting, and more.

"Add the B-roll clips to V2, apply a cross dissolve between each, color correct them to match the A-roll, and export a 1080p ProRes."

The AI handles the entire workflow through 269 tools that cover nearly every ExtendScript and QE DOM API available in Premiere Pro.

Quick Start

1. Install

Option A — npm (recommended):

npm install -g premiere-pro-mcp

Option B — Clone from source:

git clone https://github.com/ppmcp/premiere-pro-mcp.git
cd premiere-pro-mcp
npm install
npm run build

2. Install the CEP plugin

If installed via npm:

premiere-pro-mcp --install-cep

If cloned from source:

npm run install-cep

This symlinks the plugin into Premiere Pro's extensions folder and enables debug mode.

mkdir -p ~/Library/Application\ Support/Adobe/CEP/extensions
ln -s "$(pwd)/cep-plugin" ~/Library/Application\ Support/Adobe/CEP/extensions/MCPBridgeCEP

# Enable unsigned extensions (CSXS 9–14)
for v in 9 10 11 12 13 14; do
  defaults write com.adobe.CSXS.$v PlayerDebugMode 1
done

1. Copy the cep-plugin folder to %APPDATA%\Adobe\CEP\extensions\MCPBridgeCEP
2. Open Registry Editor and set these DWORD values to 1:
   • HKEY_CURRENT_USER\Software\Adobe\CSXS.12\PlayerDebugMode
   • (repeat for CSXS.9 through CSXS.14)

3. Configure your MCP client

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "premiere-pro": {
      "command": "node",
      "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"],
      "env": {
        "PREMIERE_TEMP_DIR": "/tmp/premiere-mcp-bridge"
      }
    }
  }
}

Add to your MCP server configuration:

{
  "premiere-pro": {
    "command": "node",
    "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"],
    "env": {
      "PREMIERE_TEMP_DIR": "/tmp/premiere-mcp-bridge"
    }
  }
}

Add to .cursor/mcp.json in your project or global config:

{
  "mcpServers": {
    "premiere-pro": {
      "command": "node",
      "args": ["/absolute/path/to/premiere-pro-mcp/dist/index.js"],
      "env": {
        "PREMIERE_TEMP_DIR": "/tmp/premiere-mcp-bridge"
      }
    }
  }
}

4. Start the bridge in Premiere Pro

1. Open (or restart) Premiere Pro
2. Go to Window > Extensions > MCP Bridge
3. Set the Temp Directory to match your MCP client config (e.g., /tmp/premiere-mcp-bridge)
4. Click Start Bridge — you should see a green "Running" status
5. Ask your AI assistant: "What's my current Premiere Pro project?"

Architecture

Local (stdio):

┌───────────────┐   stdio (MCP)   ┌──────────────┐   File-based IPC   ┌──────────────┐
│  AI Client    │ ◄──────────────► │  MCP Server  │ ◄────────────────► │  CEP Plugin  │
│  (Claude,     │                  │  (Node.js /  │   .jsx commands    │  (runs inside │
│   Windsurf,   │                  │   TypeScript) │   .json responses  │   Premiere)   │
│   Cursor)     │                  └──────────────┘                    └──────┬────────┘
└───────────────┘                                                             │ evalScript()
                                                                              ▼
                                                                       ┌──────────────┐
                                                                       │  Premiere Pro │
                                                                       │  ExtendScript │
                                                                       │  + QE DOM     │
                                                                       └──────────────┘

Remote (HTTP/SSE — Fly.io):

┌───────────────┐  HTTP+SSE (MCP)  ┌─────────────────────┐   File-based IPC   ┌──────────────┐
│  AI Client    │ ◄───────────────► │  MCP Server         │ ◄────────────────► │  CEP Plugin  │
│  (any MCP     │                   │  premiere-pro-mcp   │   .jsx / .json     │  (Premiere)  │
│   client)     │                   │  .fly.dev           │   shared volume    └──────────────┘
└───────────────┘                   └─────────────────────┘

1. AI client invokes an MCP tool (e.g., add_to_timeline)
2. MCP server generates ES3-compatible ExtendScript with helper functions prepended
3. Script is written to a .jsx command file in a shared temp directory
4. CEP plugin polls for command files, executes via CSInterface.evalScript()
5. Result JSON is written to a response file and returned to the AI

The file-based IPC bridge is simple, reliable, and works across macOS and Windows without network sockets.

Tools (269)

Discovery & Inspection (10 + 10)

Project Management (26)

Timeline & Editing (10 + 27 advanced)

Effects & Color (8)

Keyframes (8)

Export & Encoding (14)

Source Monitor & Playback (7 + 4)

Selection & Clipboard (7 + 6)