A Model Context Protocol server for Luma AI's Dream Machine API.
Most AI and media services work still happens through a UI a human drives. Luma Ai MCP server moves it into the conversation instead. A Model Context Protocol server for Luma AI's Dream Machine API.
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.
The server publishes 9 tools. What each one is for:
Input — - prompt (string, required): Text description of the video to generateNote — - The generation must be in a completed state to be upscaledFormat — {"identity_name": {"images": ["url1", "url2", ...]}}Returns — List of available camera motion stringsDuration — Currently, the API only supports durations of "5s" or "9s"Resolution — Valid values are "540p", "720p", "1080p", and "4k"Models — - Video generation:States — "queued", "dreaming", "completed", "failed"Upscaling — - Video generations can only be upscaled when they're in a "complete" stateConfiguration is passed through the environment: LUMA_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Luma Ai's toolset — Input, Note, Format and 6 more — is a fair guide to whether it matches your workflow. It is maintained by bobtista; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Input | - prompt (string, required): Text description of the video to generate |
| Note | - The generation must be in a completed state to be upscaled |
| Format | {"identity_name": {"images": ["url1", "url2", ...]}} |
| Returns | List of available camera motion strings |
| Duration | Currently, the API only supports durations of "5s" or "9s" |
| Resolution | Valid values are "540p", "720p", "1080p", and "4k" |
| Models | - Video generation: |
| States | "queued", "dreaming", "completed", "failed" |
| Upscaling | - Video generations can only be upscaled when they're in a "complete" state |
{
"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"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| LUMA_API_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.