How to Use the Luma AI (Generative Video & Creative) MCP in OpenAI Agents SDK

Q: How do I connect Luma AI (Generative Video & Creative) to my OpenAI Agents SDK project?

Install the required dependencies and initialize the MCPServerStreamableHttp client. Pass the server endpoint into your agent constructor to enable auto-discovery of all ten video tools.

Q: Can OpenAI Agents SDK handle long-running Luma AI (Generative Video & Creative) renders?

Yes. Since generations are asynchronous, use lm.getgeneration to poll for the status. Your agent should check the state return value until it transitions to completed.

Q: Does the Luma AI (Generative Video & Creative) server support image generation in OpenAI Agents SDK?

It does. Use lm.texttoimage to generate source frames. You can then pipe that output directly into lm.imagetovideo to create motion assets.

Q: How are API keys handled for this MCP Server?

The server expects the LUMAAPIKEY environment variable. Ensure this is set in your host environment before the agent attempts to authenticate.

Generate cinematic video assets directly within your OpenAI Agents SDK workflow using the Luma AI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Luma AI (Generative Video & Creative) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Luma AI (Generative Video & Creative) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Luma AI (Generative Video & Creative) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct video generation in OpenAI Agents SDK

Trigger `lm.text_to_video` or `lm.image_to_video` from your agent logic to render visual assets on demand. The server handles the Dream Machine API calls while your agent maintains state. Your OpenAI Agents SDK environment automatically maps these tools, allowing your agents to generate, track, and manage video queues without manual API boilerplate.

Precision camera movement for agent-driven shots

Use `lm.camera_control` to inject specific cinematics like pans, tilts, or dolly shots into your video generation requests. Define your vectors and let the model handle the interpolation. This gives your agent total command over the frame composition. Combine this with `lm.get_generation` to verify the output before your agent proceeds to the next scene in the pipeline.

Manage your Luma credits programmatically

Monitor your usage in real-time by calling `lm.get_credits` within your agent's safety loop. Prevent over-generation by checking your balance before triggering expensive render tasks. This MCP Server provides the feedback loop necessary for production systems. If credits run low, your agent can pause operations or alert you through the standard logging flow.

Setup guide

Set up Luma AI (Generative Video & Creative) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Luma AI (Generative Video & Creative) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Luma AI (Generative Video & Creative) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Luma AI (Generative Video & Creative) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Luma AI (Generative Video & Creative) Agent",
            instructions="You have access to Luma AI (Generative Video & Creative) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Luma AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Luma AI (Generative Video & Creative) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Luma AI (Generative Video & Creative) MCP in OpenAI Agents SDK

Install the required dependencies and initialize the `MCPServerStreamableHttp` client. Pass the server endpoint into your agent constructor to enable auto-discovery of all ten video tools.

Yes. Since generations are asynchronous, use `lm.get_generation` to poll for the status. Your agent should check the state return value until it transitions to completed.

It does. Use `lm.text_to_image` to generate source frames. You can then pipe that output directly into `lm.image_to_video` to create motion assets.

The server expects the `LUMA_API_KEY` environment variable. Ensure this is set in your host environment before the agent attempts to authenticate.

Your prompts are sent directly to the Luma API via the MCP protocol. No external middleman stores your creative input or generated video URLs during this transit.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript