How to Use the Luma AI (Generative Video & Creative) MCP in Google ADK

Q: How do I add Luma AI (Generative Video & Creative) to my Google ADK agent?

Use the McpToolset class and provide the HTTP URL of the server. Pass this object to your LlmAgent to register the Luma tools.

Q: How do I filter tools in Luma AI (Generative Video & Creative) for my Google ADK agent?

Use the toolnames parameter in your toolset configuration. This limits the agent to only the specific Luma functions you want to expose.

Integrate Luma AI video generation into your Google ADK agent pipelines for enterprise-grade creative workflows.

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 Google ADK

Create your Vinkius account to connect Luma AI (Generative Video & Creative) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Google ADK toolset integration

Expose the full Luma suite to your Gemini-powered agents using the `McpToolset`. This allows your agents to access `lm.text_to_video` and `lm.interpolate` alongside your existing BigQuery data. Your agents can now reason over data patterns and generate corresponding visuals in one sequence. It works within the standard Google ADK framework, keeping your agent logic centralized.

Sophisticated video extension and interpolation

Use `lm.extend_video` to add length to existing clips or `lm.interpolate` to bridge gaps between two distinct keyframes. These tools are accessible as standard Python functions in your agent code. This is ideal for extending sequences generated by your agent earlier in the session. You get granular control over the final output length and smoothness.

Efficient generation management for Google ADK

List your recent work using `lm.list_generations` to keep track of your creative output history. This helps your agent manage its own progress and clean up assets with `lm.delete_generation` when a job fails. This keeps your workspace organized and ensures you only pay for the generations you intend to keep. Your agent handles the cleanup automatically based on your defined logic.

Setup guide

Set up Luma AI (Generative Video & Creative) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Luma AI (Generative Video & Creative) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Luma AI (Generative Video & Creative)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Luma AI (Generative Video & Creative) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use the `McpToolset` class and provide the HTTP URL of the server. Pass this object to your `LlmAgent` to register the Luma tools.

The server supports both HTTP and Stdio transports. Choose the one that fits your Google ADK deployment environment best.

Your agent can hold the generation IDs and status logs from the server in its context. This allows for complex, multi-step creative planning.

Use the tool_names parameter in your toolset configuration. This limits the agent to only the specific Luma functions you want to expose.

All history is stored on Luma's servers under your account. The MCP server only acts as a thin relay, and no video data is persisted on the Vinkius infrastructure.

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