RunwayML + Luma AI

RunwayML + Luma AI is an MCP server that connects AI assistants to the RunwayML, Luma AI, and OpenRouter APIs for media generation tasks. Designed for creative developers, video producers, and automation engineers using MCP-compatible clients like Claude Desktop or Cline, this server allows language models to orchestrate text-to-video, image-to-video, and text-to-image workflows programmatically. Users can generate videos through RunwayML models like Gen-2 or Gen-3 Alpha Turbo, or via Luma AI models like Ray-2 and Ray-Flash-2. Beyond video generation, the server integrates Luma AI image synthesis with character and style reference support, alongside media management tools for querying generation history, adding audio, and upscaling video outputs to 1080p or 4K resolutions. It also includes prompt enhancement capabilities backed by OpenRouter LLMs to refine user descriptions prior to rendering. Generation tasks run asynchronously, returning immediate task tokens while delivering completion status and media URLs through progress notifications directly into the user conversation.

Category: Design, Media & Creative

Tags: image generation, luma ai, multimedia, runwayml, video generation

Visit RunwayML + Luma AI

How to install and configure RunwayML + Luma AI

1. Clone or download the repository from https://github.com/wheattoast11/mcp-video-gen and navigate to the root directory. 2. Install the necessary dependencies using npm: bash npm install 3. Build the TypeScript server: bash npm run build 4. Create a .env file in the project root with your credentials (RUNWAYML_API_SECRET, LUMAAI_API_KEY, and OPENROUTER_API_KEY). 5. Add the server configuration to your MCP client configuration file (such as Claude Desktop): json { "mcpServers": { "runway-luma-server": { "command": "node", "args": ["/path/to/runwayml-mcp-server/build/server-index.js"], "env": { "RUNWAYML_API_SECRET": "your_runwayml_api_secret_here", "LUMAAI_API_KEY": "your_luma_api_key_here", "OPENROUTER_API_KEY": "your_openrouter_api_key_here" } } } }

What you can do with RunwayML + Luma AI

• Generating custom video clips directly from text descriptions using RunwayML Gen-2 or Luma AI Ray models. * Animating static concept art or product photographs into short video clips with controlled camera motion. * Synthesizing photorealistic base images with Luma AI using style references and character consistency controls. * Enhancing creative video prompts through OpenRouter models like Claude 3.5 Sonnet before initiating media rendering. * Upscaling existing Luma AI video generations to 1080p or 4K resolution and applying custom audio tracks.

Key facts

• https://github.com/wheattoast11/mcp-video-gen
• Design, Media & Creative
• image generation, luma ai, multimedia, runwayml, video generation

Part of MCP Servers

How do I install RunwayML + Luma AI?

Clone the repository from GitHub, run npm install, and compile the TypeScript source with npm run build. Then, configure your API keys for RunwayML, Luma AI, and OpenRouter in a .env file and add the compiled script to your client configuration.

What can RunwayML + Luma AI do?

It provides tools to generate videos from text or images using RunwayML and Luma AI, create images with Luma AI, upscale existing video generations to 1080p or 4K, add audio to videos, and optimize prompts via OpenRouter models.

Which MCP clients work with RunwayML + Luma AI?

It works with any Model Context Protocol client that supports stdio process execution, such as Claude Desktop App, Cline, and other standard desktop agent environments.

How does the server handle long generation times?

For generation and upscaling tools, the server initiates the processing task and returns immediately. Progress updates and the final media URL are sent back to the MCP client through background progress notifications.