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

Q: How do I configure the Luma AI (Generative Video & Creative) MCP Server in Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. Alternatively, use the Cascade settings UI to paste your Vinkius endpoint token. Once saved, Cascade auto-discovers all ten generation tools.

Q: What happens if my Luma AI (Generative Video & Creative) credit balance runs low during a Windsurf run?

Cascade proactively runs lm.getcredits to check your balance before initiating heavy render tasks. If the balance is too low, the agent stops the pipeline and alerts you in the chat. This prevents failed API calls and wasted execution time.

Q: Can I view my recent generations directly inside the editor?

You can ask your agent to list recent work. It uses lm.listgenerations to pull your history, showing you IDs, prompts, and current states. It can then fetch specific video URLs using lm.getgeneration and display them in your workspace.

Run multi-step video generation pipelines autonomously in Windsurf with this managed 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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Multi-Step Video Pipelines in Windsurf

The `lm.text_to_video` tool lets you generate cinematic clips directly inside your workspace. Instead of prompting for each individual asset, Cascade handles the entire sequence of calls. It reads your local storyboards, writes the prompts, triggers the generation, and saves the output URLs. You can let your agent manage advanced sequences by chaining `lm.image_to_video` with `lm.extend_video`. Cascade checks your remaining balance with `lm.get_credits` before launching a run, then polls `lm.get_generation` to download the final clip. It does this without asking you for permission at every step.

Precise Camera Work via Autonomous MCP Server Control

The `lm.camera_control` tool exposes pan, tilt, zoom, and orbit commands to Windsurf. Cascade reads your camera-direction notes and maps them directly to these parameters. It eliminates manual guesswork by testing different camera paths on your source images automatically. If a camera movement fails to match your scene's composition, this MCP Server lets Cascade clean up immediately. The agent invokes `lm.delete_generation` to wipe the bad render and instantly tries a new path. This loop continues until the motion vector aligns with your project specifications.

Frame Interpolation and Motion Coherence

The `lm.interpolate` tool generates smooth transitions between two static keyframes. Cascade uses this to build consistent scenes from your design mockups. It analyzes the visual difference between your start and end frames, then triggers the generation to bridge the gap. When you need static assets first, the agent calls `lm.text_to_image` using the Photon-1 model. It then passes those generated images directly into the video tools. This creates a tight, automated loop where static concepts become moving footage in seconds.

Setup guide

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

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Luma AI (Generative Video & Creative) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Luma AI (Generative Video & Creative) payment history." If connected, Cascade will call the Luma AI (Generative Video & Creative) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "luma-ai-generative-video-creative-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, use the Cascade settings UI to paste your Vinkius endpoint token. Once saved, Cascade auto-discovers all ten generation tools.

Yes, Cascade specializes in autonomous multi-tool execution. It can run `lm.text_to_image` to create a keyframe, pass it to `lm.image_to_video`, and then call `lm.extend_video` to lengthen the clip. You only need to set the initial creative goal.

Cascade proactively runs `lm.get_credits` to check your balance before initiating heavy render tasks. If the balance is too low, the agent stops the pipeline and alerts you in the chat. This prevents failed API calls and wasted execution time.

You can ask your agent to list recent work. It uses `lm.list_generations` to pull your history, showing you IDs, prompts, and current states. It can then fetch specific video URLs using `lm.get_generation` and display them in your workspace.

Your video prompts and generation metadata run through an isolated V8 sandbox on Vinkius. No prompt data is stored persistently on the hosting platform, and the zero-trust architecture ensures your creative concepts remain private. Only the direct API calls to Luma's servers are executed.

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