Luma AI
Powered by Ray (video) and Photon (image) models by Luma AI
What is Luma AI?
Luma AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to powered by ray (video) and photon (image) models by luma ai
Powered by Ray (video) and Photon (image) models by Luma AI
This server falls under the APIs and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Powered by Ray (video) and Photon (image) models by Luma AI
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx luma-apiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Luma AI
Luma AI MCP Server connects AI assistants directly to Luma AI's generation APIs, enabling image creation via the Photon model and video creation via the Ray model through natural language prompts. Users can specify aspect ratios, quality settings, reference images, character references, and keyframe control for videos — all from within their MCP client conversation. It is designed for creative professionals and developers who want to integrate state-of-the-art generative media into AI-driven workflows without leaving their chat interface.
Prerequisites
- Python 3.10 or later installed
- A Luma AI account with an active API key (obtain from https://lumalabs.ai/api/keys)
- An MCP client such as Claude Desktop
- The Luma API MCP repository cloned locally (uses a setup.sh script for configuration)
Clone the repository
Clone the luma-api-mcp repository to your local machine. The setup is handled by a shell script rather than a package manager.
git clone https://github.com/lumalabs/luma-api-mcp.git
cd luma-api-mcpObtain your Luma AI API key
Visit https://lumalabs.ai/api/keys, sign in to your Luma AI account, and generate an API key. Copy the key — you will provide it during setup.
Run the setup script
Execute the setup script which installs dependencies and prompts you for your API key. The script configures the server so it can authenticate with Luma AI.
sh setup.shConfigure your MCP client
Add the Luma AI MCP server to your client configuration. Pass your Luma API key as the LUMAAI_API_KEY environment variable so the server can authenticate with Luma's services.
{
"mcpServers": {
"luma-api": {
"command": "python",
"args": ["server.py"],
"cwd": "/path/to/luma-api-mcp",
"env": {
"LUMAAI_API_KEY": "your-luma-api-key"
}
}
}
}Understand the two generation tools
The server exposes two main tools. create_image generates images using the Photon (photon-1) or Photon Flash (photon-flash-1) models with parameters for aspect ratio, style references, and up to 8 image reference inputs with weights. create_video generates videos using Ray 2 (ray-2), Ray Flash 2 (ray-flash-2), or Ray 1.6 (ray-1-6) with configurable aspect ratio, resolution (540p to 4K), duration (5s or 9s), looping, and keyframe control.
Luma AI Examples
Client configuration
Claude Desktop configuration to launch the Luma AI MCP server with API key authentication.
{
"mcpServers": {
"luma-api": {
"command": "python",
"args": ["server.py"],
"cwd": "/path/to/luma-api-mcp",
"env": {
"LUMAAI_API_KEY": "your-luma-api-key"
}
}
}
}Prompts to try
Use these prompts with Claude to generate images and videos through Luma AI.
- "Generate a photorealistic image of a mountain lake at golden hour in 16:9 aspect ratio"
- "Create an image using photon-flash-1 of a futuristic cityscape at night"
- "Make a 5-second looping video of ocean waves using ray-2 in 4K resolution"
- "Generate a video starting with a sunrise and ending with a sunset, 9 seconds long"
- "Create an image of a dragon with a style reference from this image URL"Troubleshooting Luma AI
API key rejected or 401 authentication error
Verify that LUMAAI_API_KEY is set to a valid active API key from https://lumalabs.ai/api/keys. The key must be from an account with API access enabled — free accounts may not have API access by default.
Image generation times out
Image generation via Photon typically takes 5-15 seconds. If your MCP client has a short timeout, increase it. Video generation with Ray takes 15-60 seconds depending on duration and resolution — do not cancel prematurely.
Video keyframe parameters are not applied
Keyframes must be specified as image URLs or generation IDs from prior Luma generations. Ensure the referenced image URLs are publicly accessible and that generation IDs correspond to completed (not pending) generations.
Frequently Asked Questions about Luma AI
What is Luma AI?
Luma AI is a Model Context Protocol (MCP) server that powered by ray (video) and photon (image) models by luma ai It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Luma AI?
Follow the installation instructions on the Luma AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Luma AI?
Luma AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Luma AI free to use?
Yes, Luma AI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Luma AI Alternatives — Similar APIs Servers
Looking for alternatives to Luma AI? Here are other popular apis servers you can use with Claude, Cursor, and VS Code.
Kong
★ 43.4k🦍 The API and AI Gateway
API Mega List
★ 5.4kThis GitHub repo is a powerhouse collection of APIs you can start using immediately to build everything from simple automations to full-scale applications. One of the most valuable API lists on GitHub—period. 💪
Fetch
★ 5.4kFetch web content and convert to markdown for AI consumption
Fusio
★ 2.1kSelf-Hosted API Management for Builders
Korean Law
★ 1.8k국가법령정보MCP v4.0 | 법제처 41개 API → 17개 MCP 도구. 법령·판례·조례 검색 + LLM 환각 방지 인용검증 + 조문 영향 그래프(impact_map) + 시점 비교 자동 diff(time_travel) + 시민 5단계 실행 가이드(action_plan) | 41 Korean legal APIs → 17 MCP tools
RuleGo
★ 1.5k⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
Browse More APIs MCP Servers
Explore all apis servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Luma AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Luma AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.