🎬 Runway MCP Server

A Model Context Protocol (MCP) server for Runway AI - featuring Gen-4 models, Aleph video editing, and comprehensive video generation tools.

MCP Registry Name: io.github.sidart10/runway-mcp-server

✨ Features

• 🎥 Aleph Video Editing - Add/remove objects, change camera angles, transform lighting
• 🎨 Gen-4 Image Generation - High-fidelity images with reference support
• 📹 Gen-4 Video Generation - Text-to-video, image-to-video, keyframe control
• 🎭 Advanced Tools - Video extension, 4K upscaling, style transfer

📦 Installation

⚠️ Note: The root-level runway_mcp_server.py file is kept for backward compatibility. New installations should use the PyPI package below.

Option 1: Install from PyPI (Recommended)

# Install with uvx (automatically manages dependencies)
uvx runway-mcp-server

# Or install globally with pip
pip install runway-mcp-server

Option 2: Install from Source

# Clone the repository
git clone https://github.com/sidart10/runway-mcp-server.git
cd runway-mcp-server

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # Mac/Linux (or venv\Scripts\activate on Windows)

# Install in development mode
pip install -e .

🚀 Quick Start

1. Configure API Key

Create a .env file in the project root:

# .env file
RUNWAY_API_KEY=your_api_key_here

Get your API key from dev.runwayml.com

2. Add to MCP Config

For Cursor: Edit ~/.cursor/mcp.json

For Claude Desktop: Edit ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "runway": {
      "command": "uvx",
      "args": ["runway-mcp-server"],
      "env": {
        "RUNWAY_API_KEY": "your_api_key_here"
      }
    }
  }
}

Note: Replace your_api_key_here with your actual Runway API key from dev.runwayml.com

3. Restart Your Client

Restart Cursor or Claude Desktop to load the server.

🛠️ Available Tools

Tool	Description
generate_image_gen4	Create high-quality images with Gen-4
generate_video_text_to_video	Generate videos from text descriptions
generate_video_image_to_video	Animate images with motion
generate_video_first_last_frame	Precise start/end frame control
edit_video_with_aleph	⭐ Advanced video editing & transformation
restyle_video	Apply artistic styles to videos
extend_video	Extend videos by 5-10 seconds
upscale_video_4k	Upscale to 4K resolution
get_task_status	Check generation progress
cancel_task	Cancel running tasks
list_available_models	List all available models
get_api_info	Server configuration info

📚 Documentation

• Quick Start Guide - Get running in 5 minutes
• Aleph Guide - Video editing deep dive
• Features Guide - All capabilities explained
• Architecture - Technical details
• Examples - Working code samples

📁 Project Structure

runway-mcp-server/
├── runway_mcp_server.py    # Main server code
├── requirements.txt         # Python dependencies
├── .env                     # API key (create this)
├── README.md               # This file
├── .gitignore              # Git ignore rules
├── venv/                   # Virtual environment
├── docs/                   # Documentation
│   ├── QUICKSTART.md
│   ├── ALEPH_GUIDE.md
│   ├── FEATURES.md
│   ├── ARCHITECTURE.md
│   └── ...
├── examples/               # Code examples
│   └── example_usage.py
└── config/                 # Configuration templates
    └── mcp_config_example.json

💡 Usage Examples

Generate a Video

"Generate a 10-second video of an eagle soaring over mountains at sunset"

Edit with Aleph

"Edit this video to remove the person in the background: [video URL]"

Create an Image

"Create a Gen-4 image of a futuristic cyberpunk city at night, 1920x1080"

🔒 Rate Limits

• API calls are rate-limited based on your Runway plan
• Gen-4 Turbo: ~5 credits per second
• Aleph editing: ~15 credits per second
• Check usage at dev.runwayml.com

🐛 Troubleshooting

API Key Not Loading:

# Verify .env file exists
ls -la .env

# Check if key loads
python -c "from dotenv import load_dotenv; import os; load_dotenv(); print('✅' if os.getenv('RUNWAY_API_KEY') else '❌')"

Server Won't Start:

• Ensure Python 3.10+ is installed: python3 --version
• Verify virtual environment is activated
• Check all dependencies installed: pip list

Task Timeouts:

• Video generation takes 2-10 minutes depending on length
• Use get_task_status() to check progress
• Increase wait time if needed

🤝 Contributing

This is an MCP server implementation following the Model Context Protocol specification.

📄 License

This MCP server is provided as-is for use with the Runway API. Runway API usage is subject to Runway's terms of service.

🔗 Resources

• Runway Developer Portal: dev.runwayml.com
• API Documentation: docs.dev.runwayml.com
• MCP Specification: modelcontextprotocol.io
• Help Center: help.runwayml.com

---

Built for the Runway AI community 🚀

For issues or questions, refer to the Runway Developer Portal or check the documentation.