leancoderkavy/premiere-pro-mcp

Adobe Premiere Pro MCP — independent, local-first server for supported workflows. Connect Claude, Codex, or Cursor through a local CEP bridge.

What it solves

Video editors and post-production teams often repeat tedious tasks in Adobe Premiere Pro: importing media, arranging clips, applying effects, adjusting keyframes, and exporting. This project gives AI assistants a structured way to drive Premiere directly, so an editor can ask in plain language to perform complex edits and get a reviewable, local-first workflow instead of manually clicking through the timeline.

How it works

The project is an MCP (Model Context Protocol) server that runs locally and bridges compatible AI clients (Claude, Cursor, Codex, GitHub Copilot, etc.) to Premiere Pro. It uses Adobe’s official UXP and CEP/ExtendScript APIs to expose 434 core tools across 67 modules, covering project inspection, timeline editing, export planning, and verification. A separate connector installs into Premiere, and the server checks the connection with verify_premiere_connection before any changes. Tools can be guarded with an expected project path to prevent accidental edits to the wrong project, and many operations return readback receipts so the assistant knows whether Premiere applied the change as verified, committed-unverified, or failed.

Who it’s for

Editors, post-production leads, and developers who want to automate Premiere Pro workflows with AI assistants. It’s designed for local, reviewable automation—useful for testing repeatable edits on duplicate projects, building AI-assisted editing pipelines, or integrating Premiere into a larger agent-based production toolchain.

Highlights

  • 434 core tools plus 96 capability-gated UXP tools, covering media import, sequence editing, effects, keyframes, export, and After Effects MOGRT handoffs.
  • Local-first and MIT-licensed; runs on Windows and macOS with Premiere Pro 2020–2026.
  • Emphasizes safety: optional expected_project_path guards, single-use confirmation tokens for risky operations, and readback receipts for verified outcomes.
  • Supports guided workflows for editorial planning, review, and delivery, with explicit boundaries on what is verified versus assumed.
  • Compatible with modern MCP protocol (2026-07-28) while offering a legacy mode for older clients.

Related

  • Project
    hetpatel-11/Adobe_Premiere_Pro_MCP

    This project provides a Model Context Protocol (MCP) server that connects AI assistants like Codex and Claude to a local Adobe Premiere Pro installation. It exposes 283 editing tools, context resources, and prompts, allowing models to inspect, edit, and export projects through a CEP panel bridge.

  • Project
    loonghao/photoshop-python-api-mcp-server

    A Model Context Protocol (MCP) server that allows AI assistants to programmatically control Adobe Photoshop on Windows for tasks like document creation and layer manipulation.

  • Project
    samuelgursky/davinci-resolve-mcp

    An MCP server that lets AI assistants control DaVinci Resolve video editing software through its official scripting API, with full editing, grading, and rendering capabilities, plus an offline file-level server for cloud workflows.

  • Project
    tomyud1/godot-mcp

    Godot MCP is a Godot 4.4+ plugin that lets an MCP‑compatible AI (Claude, Cursor, etc.) control the editor via a local Node.js server. It provides 69 tools for scene editing, script/file management, running the game, undo/redo, asset generation and a browser‑based visualizer, enabling AI‑driven game development directly inside Godot.

  • Project
    wonderwhy-er/DesktopCommanderMCP

    Desktop Commander is an MCP server that enables AI assistants to perform local file management, execute terminal commands, and handle data analysis directly on your computer.