luma_upscale

THE RISK

Medium Risk

Why luma_upscale needs a policy

Upscaling creates a new higher-resolution version of an existing generation, which is a write/modify operation. It does not delete or overwrite the original irreversibly, and it doesn't execute code or move money. The blast radius is medium since it consumes API credits and modifies a generation asset.

From the tool's definition Upscales a specific Luma AI generation to a higher resolution

Documented attack patterns abuse exactly the kind of access luma_upscale gives an agent:

POLICY

How to control luma_upscale

PolicyLayer is an MCP gateway — it sits between your AI agents and RunwayML + Luma AI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for luma_upscale:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "luma_upscale": {
      "limits": [
        {
          "counter": "luma_upscale_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

luma_upscale stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register RunwayML + Luma AI MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More RunwayML + Luma AI MCP Server tools

Destructive luma_delete_generation Deletes a specific Luma AI generation. Execute generate_image_to_video Generates a video from an image using RunwayML or Luma AI. Execute generate_text_to_video Generates a video from text using RunwayML or Luma AI. Write enhance_prompt Uses an LLM (via OpenRouter) to refine a prompt for video generation. Write luma_add_audio Adds audio to a specific Luma AI generation based on a prompt. Write luma_generate_image Generates an image using Luma AI. Read luma_get_camera_motions Lists supported camera motions for Luma AI prompts. Read luma_get_generation Gets details for a specific Luma AI generation.

All 10 RunwayML + Luma AI MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about luma_upscale

What does the luma_upscale tool do? +

Upscales a specific Luma AI generation to a higher resolution. It is categorised as a Write tool in the RunwayML + Luma AI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on luma_upscale? +

Register the RunwayML + Luma AI MCP Server MCP server in PolicyLayer and add a rule for luma_upscale: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches RunwayML + Luma AI MCP Server. Nothing to install.

What risk level is luma_upscale? +

luma_upscale is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit luma_upscale? +

Yes. Add a rate_limit block to the luma_upscale rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block luma_upscale completely? +

Set action: deny in the PolicyLayer policy for luma_upscale. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides luma_upscale? +

luma_upscale is provided by the RunwayML + Luma AI MCP Server MCP server (wheattoast11/mcp-video-gen). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every RunwayML + Luma AI MCP Server tool call.

Start from RunwayML + Luma AI MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →