# Luma AI MCP Server

> Dream Machine API in MCP form: Ray 2 video, Photon images, extend and interpolate.

- **Category:** Video Generation
- **Vendor:** Community (bobtista) (community)
- **Pricing:** paid
- **Verified:** 2026-06-11

## What it does

Community Python server for Luma's Dream Machine API v1: text/image-to-video on ray-2 and ray-flash-2, video extension and interpolation, Photon image generation, upscaling, audio addition and credit checks. Luma has no official MCP, so this is the main direct-API option.

## Connect

- Claude Code: `claude mcp add luma -- uv run --project /path/to/luma-ai-mcp-server -m luma_ai_mcp_server`
- Local: `uv run --project /path/to/luma-ai-mcp-server -m luma_ai_mcp_server`

**Auth:** api_key (env `LUMA_API_KEY`) — https://lumalabs.ai/dream-machine/api

## Capabilities

`text-to-video` · `image-to-video` · `video-extension` · `interpolation` · `text-to-image` · `upscaling`

## Sample tools

`create_generation` · `get_generation` · `list_generations` · `upscale_generation` · `add_audio` · `generate_image` · `get_credits` · `get_camera_motions`

## Field notes

MIT but tiny (6 stars) — functional rather than polished; runs from a cloned repo via uv. Luma Ray models are also reachable through fal, Replicate, Runway and PiAPI hub MCPs.

## Links

- Docs: https://docs.lumalabs.ai/docs/api
- Repo: https://github.com/bobtista/luma-ai-mcp-server

---

Structured data: https://mcp.film/api/mcps/luma.json · Directory: https://mcp.film