Luma AI MCP Server 🎥

A Model Context Protocol server for Luma AI's Dream Machine API.

Overview

This MCP server integrates with Luma AI's Dream Machine API (v1) to provide tools for generating, managing, and manipulating AI-generated videos and images via Large Language Models. It implements the Model Context Protocol (MCP) to enable seamless interaction between AI assistants and Luma's creative tools.

Features ✨

• Text-to-video generation
• Advanced video generation with keyframes
• Image-to-video conversion
• Video extension and interpolation
• Image generation with reference images
• Audio addition to videos
• Video upscaling
• Credit management
• Generation tracking and status checking

Tools 🛠️

1. `ping`

2. `create_generation`

3. `get_generation`

4. `list_generations`

5. `delete_generation`

6. `upscale_generation`

7. `add_audio`

8. `generate_image`

9. `get_credits`

10. `get_camera_motions`

Setup for Claude Desktop 🖥️

1. Get your Luma API key from Luma AI (sign up or log in to get your API key)

2. Add this to your Claude Desktop configuration file:

{
     "mcpServers": {
       "luma": {
         "command": "uv",
         "args": [
           "run",
           "--project",
           "/path/to/your/luma-ai-mcp-server",
           "-m",
           "luma_ai_mcp_server"
         ],
         "env": {
           "LUMA_API_KEY": "your-luma-api-key-here"
         }
       }
     }
   }

Replace:

3. Restart Claude Desktop

4. That's it! You can now use Luma AI tools directly in Claude Desktop conversations.

Quick Troubleshooting 🛠️

If you're having issues:

1. Check your API key is correct

2. Make sure the path to the server is correct

3. View logs with: `tail -n 20 -f ~/Library/Logs/Claude/mcp*.log`

Advanced Video Generation Types 🎬

The Luma API supports various types of advanced video generation through keyframes:

1. Starting from an image: Provide `frame0` with `type: "image"` and an image URL

2. Ending with an image: Provide `frame1` with `type: "image"` and an image URL

3. Extending a video: Provide `frame0` with `type: "generation"` and a generation ID

4. Reverse extending a video: Provide `frame1` with `type: "generation"` and a generation ID

5. Interpolating between videos: Provide both `frame0` and `frame1` with `type: "generation"` and generation IDs

API Limitations and Notes 📝

• Duration: Currently, the API only supports durations of "5s" or "9s"
• Resolution: Valid values are "540p", "720p", "1080p", and "4k"
• Models:
  • Video generation:
    • "ray-2" (default) - Best quality, slower
    • "ray-flash-2" - Faster generation
    • "ray-1-6" - Legacy model
  • Image generation:
    • "photon-1" (default) - Best quality, slower
    • "photon-flash-1" - Faster generation
• Generation types: Video, image, and advanced (with keyframes)
• Aspect Ratios: "1:1" (square), "16:9" (landscape), "9:16" (portrait), "4:3" (standard), "3:4" (standard portrait), "21:9" (ultrawide), "9:21" (ultrawide portrait)
• States: "queued", "dreaming", "completed", "failed"
• Upscaling:
  • Video generations can only be upscaled when they're in a "complete" state
  • Target resolution must be higher than the original generation's resolution
  • Each generation can only be upscaled once
• API Key: Required in environment variables
• API Version: Uses Dream Machine API v1

License 📄

MIT