Use Luma AI with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Generate cinematic AI videos and images via Luma. use Dream Machine for text-to-video, image-to-video, and professional camera control.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete Luma AI capability set.
These are the exact actions your AI can choose when you ask it to work with Luma AI.
01-04
4 capabilities in this set.
Part of 10 available through Luma AI.
- 01
Lm.delete generation
Delete a Luma Dream Machine generation and its video
- 02
Lm.extend video
Extend an existing Luma video with additional footage. Seamlessly continues the scene
- 03
Lm.interpolate
Create smooth video transition between two keyframe images using Luma Dream Machine
- 04
Lm.get credits
Get current Luma Dream Machine credit balance
05-07
3 capabilities in this set.
Part of 10 available through Luma AI.
- 05
Lm.image to video
Animate a still image into video using Luma Dream Machine. Image becomes the first frame
- 06
Lm.text to video
), and loop (true/false). Poll get_generation for results. Generate cinematic AI video from a text prompt using Luma Dream Machine (Ray-2 model). Industry-leading motion coherence and photorealism
- 07
Lm.camera control
Generate video with specific camera movements using Luma Dream Machine. Supports pan, tilt, dolly, orbit
08-10
3 capabilities in this set.
Part of 10 available through Luma AI.
- 08
Lm.get generation
Get the status and result of a Luma Dream Machine generation. Returns state (queued/dreaming/completed/failed) and video URL
- 09
Lm.list generations
List recent Luma Dream Machine generations. Returns generation IDs, prompts, states, and timestamps
- 10
Lm.text to image
Generate photorealistic images using Luma Photon-1 model
Observed, not estimated
946ms average. Fast in production.
Luma AI is checked daily against the live service.
- Fastest day
- 784ms
- Slowest day
- 1133ms
- 14-day trend
- Slowing+18%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Luma AI, so you can see the experience inside your AI.
It does not authenticate your account with Luma AI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Luma AI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_eMuspQUEffZmIoaVTe2vhE8crBGgBQMVGBLmfs0C/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Luma AI capabilities are ready to use.
{
"mcpServers": {
"luma-ai-generative-video-creative-mcp": {
"url": "https://edge.vinkius.com/vk_preview_eMuspQUEffZmIoaVTe2vhE8crBGgBQMVGBLmfs0C/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Luma AI owners ask.
- 01
How do I check if my video generation is finished?
Use the lm.get_generation capability with the Generation ID provided. Your agent will poll the Luma API and report the current state (queued, dreaming, or completed). Once finished, it will return the final MP4 video URL.
- 02
Can I control the camera movement in my AI-generated video?
Absolutely. Use the lm.camera_control capability. You can provide a scene prompt and a JSON block defining the movement type (e.g., orbit, pan, tilt) and magnitude, allowing for professional cinematographic directing.
- 03
Can my agent extend an existing Luma video with more footage?
Yes. The lm.extend_video capability allows you to provide a continuation prompt and a previous Generation ID. Your agent will trigger Luma to seamlessly expand the scene, maintaining visual and structural consistency.
Explore
More in AI Frontier
Runway ML AI Connector
Empower your AI with Runway ML's advanced video generation capabilities to seamlessly create, animate, and int
ViewSynthesia AI Connector
Produce professional AI videos with lifelike avatars that present in 140+ languages without cameras, studios,
ViewHeyGen AI Connector
Create AI-generated videos with realistic digital avatars that speak in any language for training, marketing,
ViewColossyan AI Connector
Automate AI video creation via Colossyan — generate videos from templates, manage avatars, and track rendering
View
Suggestions
Leonardo.ai (Generative AI & Models) AI Connector
Generate high-fidelity images via Leonardo.ai — orchestrate generations, audit AI models, and manage visual as
ViewElai AI Video AI Connector
Equip your AI agent to generate AI videos, manage avatars, and track rendering status via the Elai.io API.
ViewSynthesia AI Connector
Connect your AI to Synthesia. Generate corporate AI avatar videos from text prompt, explore templates, and aut
ViewSpiritme AI Connector
Create AI-generated videos with digital human presenters that deliver personalized messages in multiple langua
View
