# Luma API MCP

> Luma's own two-tool MCP server for Ray video and Photon stills.

- **Category:** Video Generation
- **Vendor:** Luma AI (official)
- **Pricing:** paid
- **Verified:** 2026-10-21

## What it does

Luma Labs' first-party MCP server, published from the lumalabs GitHub org, exposing exactly two tools: create_image on photon-1 and photon-flash-1, and create_video on ray-2, ray-flash-2 and ray-1-6. create_video takes frame0 and frame1 references, so an agent can pin both ends of a shot and chain continuity across a sequence; create_image accepts image, style, character and modify references for consistent looks. Narrow by design — no polling, extension or upscaling tools — but it is the only Luma-maintained MCP that exists.

## Connect

- Local: `Clone github.com/lumalabs/luma-api-mcp and run `sh setup.sh`, which installs jq, uv and Python 3.10, prompts for LUMA_API_KEY, and registers the server in claude_desktop_config.json as `uv run --python python3.10 --with mcp[cli] --with aiohttp mcp run` against server.py.`

**Auth:** api_key (env `LUMA_API_KEY`) — <https://lumalabs.ai/api/keys>

## Capabilities

[text-to-video](https://mcp.film/capabilities/text-to-video.md) · [image-to-video](https://mcp.film/capabilities/image-to-video.md) · [text-to-image](https://mcp.film/capabilities/text-to-image.md) · `keyframe-control` · `style-reference` · `character-reference`

## Sample tools

`create_image` · `create_video`

## Field notes

Official but frozen: MIT, 26 stars, 11 forks, created 2025-04-15 and last pushed 2025-04-18 (still true on 2026-10-21), two open issues, no releases and no package on PyPI. It speaks the Dream Machine API only — Luma's current Agents API (uni-1, uni-1-max, ray-3.2 at agents.lumalabs.ai/v1 under LUMA_AGENTS_API_KEY) is not supported here or in any other MCP server, and the Agents API docs still mention no MCP as of 2026-10-21. The documented install path only writes Claude Desktop's config file; there is no vendor-published `claude mcp add` form, hence the null above rather than a command we made up. For a wider Dream Machine tool surface use the community `luma` server; for ray-3.2 today, reach it through the fal, Replicate or Runway hub MCPs.

## Alternatives

- [Kling MCP (Official)](https://mcp.film/mcps/kling-official.md) — Kling's own hosted MCP: text and image to video or stills, over OAuth on your Kling credits.
- [Google GenMedia MCP](https://mcp.film/mcps/google-genmedia.md) — Google Cloud's MCP servers for Veo, Gemini Omni, Lyria, Chirp TTS and ffmpeg compositing.
- [Pika MCP](https://mcp.film/mcps/pika.md) — Pika's hosted media toolkit: 57 apps and models for video, image, audio and edit, from mcp.pika.art.
- [Higgsfield MCP](https://mcp.film/mcps/higgsfield.md) — Hosted connector to 30+ models: Seedance 2.5, Kling 3, Soul 2.0, Nano Banana Pro.
- [varg](https://mcp.film/mcps/varg.md) — Brief-to-ad video agent over 100+ models, with a cost estimate before every render.
- [MiniMax MCP](https://mcp.film/mcps/minimax.md) — Official MiniMax server: Hailuo video, image gen, TTS and voice cloning.

## Verification

- Status: Freshly checked (3 days old)
- Added: 2026-09-08
- Last verified: 2026-10-21
- Machine JSON: https://mcp.film/api/mcps/luma-official.json

## Links

- Site: https://lumalabs.ai/api?utm_source=mcp.film&utm_medium=referral&utm_campaign=directory&utm_content=luma-official%3Asite
- Docs: https://github.com/lumalabs/luma-api-mcp?utm_source=mcp.film&utm_medium=referral&utm_campaign=directory&utm_content=luma-official%3Adocs#readme
- Repo: https://github.com/lumalabs/luma-api-mcp

---

Structured data: https://mcp.film/api/mcps/luma-official.json · Directory: https://mcp.film
Canonical: https://mcp.film/mcps/luma-official/
Hosted directory MCP: https://mcp.film/mcp