mcp server

openreelio

Prompt-driven AI video editor for Shorts and long-form. (0.0.0 <= v < 0.5.0: [Pre-Alpha])

openreelio/openreeliocommunitylistedunreviewednot running here yet

Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

Node.js 20 or newer

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "openreelio-openreelio": {
      "command": "npx",
      "args": [
        "-y",
        "openreelio-cli"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 14, 2026

OpenReelio

AI-Powered Video Editor for Creators

Features • Installation • Documentation • Contributing

Overview

OpenReelio is an AI-powered desktop video editor designed for content creators. Built with a prompt-first approach, it combines the power of modern AI with professional editing capabilities.

Key Concepts

Prompt-First Editing: Describe what you want in natural language
Event Sourcing: Complete edit history with unlimited undo/redo
AI Agent-Driven: Parallel processing, automatic analysis, source generation
IDE-like Experience: Familiar interface for developers and creators

Features

Core Editing

Non-linear timeline with multi-track support
Clip splitting, trimming, and repositioning
Effects and transitions
Audio mixing and synchronization
Caption/subtitle support with styling

AI Integration

Natural language edit commands
Automatic scene detection (early stage)
Speech-to-text transcription (optional build feature)
Smart asset search (optional build feature)
AI-generated edit suggestions

Plugin System

WASM-based plugin runtime
Provider interfaces for assets, presets, and templates
Backend integration in place; plugin UX is planned

Quality Control

QC framework with built-in rules
Black frame, audio peak, and caption checks (currently heuristic, early stage)
Auto-fix suggestions planned as the checks mature

Performance

GPU-accelerated encoding (NVENC, AMF, QSV, VideoToolbox)
Parallel proxy generation
Efficient memory pooling
Smart caching with LRU/LFU eviction

Tech Stack

Layer	Technology
Framework	Tauri 2.x
Backend	Rust
Frontend	React 18 + TypeScript
State	Zustand + Immer
Styling	Tailwind CSS
Video	FFmpeg
Plugins	WebAssembly (Wasmtime)
Database	SQLite

Installation

Pre-built Binaries (Recommended)

Download the latest release from the Releases page. Installers bundle everything OpenReelio needs at runtime, including FFmpeg/FFprobe and the OpenReelio CLI used for local MCP integration. Automatic updates are delivered through the signed latest.json manifest on GitHub Releases. OS code signing is not yet configured, so Windows and macOS may show a first-run warning (see below).

Windows

Download OpenReelio-x.x.x-windows-x64.msi
Run the installer
If you see "Windows protected your PC":
- Click "More info"
- Click "Run anyway"

macOS

Download OpenReelio-x.x.x-macos-x64.dmg (Intel) or OpenReelio-x.x.x-macos-arm64.dmg (Apple Silicon)
Open the DMG and drag to Applications
If you see "cannot be opened":
- Right-click the app → "Open"
- Click "Open" in the dialog

Linux

Download OpenReelio-x.x.x-linux-x64.AppImage
Make executable: chmod +x OpenReelio-*.AppImage
Run: ./OpenReelio-*.AppImage

From Source

Prerequisites:

Rust 1.88+
Node.js 20+
FFmpeg 6+ (optional): a system FFmpeg/FFprobe on PATH is used if present; otherwise the first debug build automatically downloads bundled binaries into src-tauri/binaries (sources pinned in scripts/ffmpeg-sources.json; opt out with SKIP_FFMPEG_DOWNLOAD=1)
(Optional) LLVM/Clang for Whisper: building with --features whisper requires libclang (bindgen). On Windows, install LLVM and set LIBCLANG_PATH to the folder containing libclang.dll.

# Clone the repository
git clone https://github.com/openreelio/openreelio.git
cd openreelio

# Install dependencies
npm install

# Run in development mode
npm run tauri dev

# Build for production
npm run tauri build

Documentation

Using OpenReelio as a Tool (AI Agents)

OpenReelio ships a headless CLI and MCP server so coding agents (Claude Code, Codex, Cursor) can edit, analyze, render, and verify video autonomously. Start with the Agent Guide, or bootstrap directly:

npx openreelio-cli help-json                        # machine-readable command surface
npx openreelio-cli mcp --project <dir> --stdio      # MCP server (read-only by default)

Every path an MCP client sends resolves inside the project directory. A relative path is joined onto the project root, and absolute paths outside it, .. escapes, UNC/network paths and URLs are rejected before they reach the filesystem or FFmpeg — so render into the project before asking the server to read, sheet or verify a file. The project's own imported media is the one exception: it is read wherever the user put it, because the app imports by reference, but media on a UNC or network path is still refused lexically and media this machine cannot read is refused as missing.

Project Structure

openreelio/
├── src/                    # React frontend
│   ├── components/         # UI components
│   ├── stores/             # Zustand stores
│   └── types/              # TypeScript types
├── src-tauri/              # Rust backend
│   └── src/
│       ├── core/           # Core engine
│       │   ├── ai/         # AI integration
│       │   ├── commands/   # Edit commands
│       │   ├── plugin/     # Plugin system
│       │   ├── qc/         # QC automation
│       │   └── ...
│       └── ipc/            # Tauri IPC layer
└── docs/                   # Documentation

Contributing

We welcome contributions! Please see our Contributing Guide for details.

Quick Start

Fork the repository
Create a feature branch (git checkout -b feat/amazing-feature)
Commit your changes (git commit -m 'feat: add amazing feature')
Push to the branch (git push origin feat/amazing-feature)
Open a Pull Request

Development

# Run frontend tests
npm test

# Run Rust tests
cd src-tauri && cargo test

# Run linter
npm run lint
cargo clippy

Notes:

Windows PowerShell may block npm due to npm.ps1 execution policy. Use npm.cmd ... (or adjust PowerShell execution policy) if you see PSSecurityException.

Roadmap

v0.1.x (Current)

Core timeline editing
Effects and transitions
Audio mixing
Export pipeline (7 presets)
Release and distribution (signed auto-updates, bundled FFmpeg + CLI)
Speech-to-text transcription (Whisper, optional build feature)

AI agent workflow hardening
Smart asset search (optional build feature)

Future

Video generation (Sora, Runway)
Collaboration features
Cloud project sync
Mobile companion app

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Tauri for the amazing desktop framework
FFmpeg for video processing
All our contributors