mcpField
L
Luma API MCP

Luma API MCP

Local
lumalabs.aiDeveloper Tools26Updated 80w ago
RepositoryVisit website

About Luma API MCP

Luma API MCP is an MCP server that calls Luma AI's Photon image models and Ray video models through the Luma API. It is intended for users who want to generate images and videos directly from MCP clients such as Claude Desktop.

Key features

  1. 01Image generation with Photon models
  2. 02Video generation with Ray models
  3. 03Multiple aspect ratios and reference image inputs
  4. 04Keyframe control with start and end frame images
  5. 05Setup script that prompts for the API key

Use cases

  1. 01Generating images from text prompts in Claude Desktop
  2. 02Creating looping or transition videos from keyframes
  3. 03Guiding character or style with reference images

MCP support

This project is an MCP server that exposes image and video generation to MCP clients, calling the Luma API with parameters such as prompt, aspect_ratio and model.

#python#api#image#video#mcp#photon#ray#luma#lumaai#genai#model-context-protocol#mcp-servers#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Luma API MCP

Setup

  1. Install Claude Desktop App or any MCP client
  2. Get API Key from https://lumalabs.ai/api/keys
  3. Run sh setup.sh, here it will ask the API Key - paste it from 2.

Run

Open Claude Desktop or any MCP client

Features

Create Image
  • prompt: text
  • aspect_ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "21:9", "9:21" (default: "16:9")
  • model: "photon-1", "photon-flash-1" (default: "photon-1")
  • image_ref: list of image URLs with weights to influence generation (optional), max 8
  • style_ref: single image URL with weight to influence style (optional), max 1
  • character_ref: list of character image URLs (optional), max 4
  • modify_image_ref: single image URL to modify with weight (optional), max 1
Create Video
  • prompt: text
  • aspect_ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "21:9", "9:21" (default: "16:9")
  • model: "ray-2", "ray-flash-2", "ray-1-6" (default: "ray-2")
  • loop: boolean (default: false)
  • resolution: "540p", "720p", "1080p", "4k" (default: "720p")
  • duration: "5s", "9s" (default: "5s")
  • frame0_image: image URL (optional)
  • frame1_image: image URL (optional)
  • frame0_id: generation ID (optional)
  • frame1_id: generation ID (optional)

Technical Notes

  • Keyframes: Providing frame0_image/frame1_image gives more control over video start/end points
  • Video Response Time: Typical video generation takes 15-60 seconds depending on duration and resolution
  • Image Response Time: Typical generation takes 5-15 seconds depending on model complexity

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.