generate_image_to_video

THE RISK

High Risk

Why generate_image_to_video needs a policy

This tool initiates an external computational operation (video generation) via RunwayML or Luma AI APIs. It is not a simple read, nor does it delete data or move money. The effects depend on the input image and parameters passed, and it triggers real API calls that consume credits/quota.

From the tool's definition 'Generates a video from an image using RunwayML or Luma AI' — triggers an external AI generation operation on a third-party API

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

POLICY

How to control generate_image_to_video

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 generate_image_to_video:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_image_to_video": {
      "limits": [
        {
          "counter": "generate_image_to_video_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

generate_image_to_video stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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.

RATE-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_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. Write luma_upscale Upscales a specific Luma AI generation to a higher resolution. 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 →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in RunwayML + Luma AI MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about generate_image_to_video

What does the generate_image_to_video tool do? +

Generates a video from an image using RunwayML or Luma AI. It is categorised as a Execute tool in the RunwayML + Luma AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on generate_image_to_video? +

Register the RunwayML + Luma AI MCP Server MCP server in PolicyLayer and add a rule for generate_image_to_video: 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 generate_image_to_video? +

generate_image_to_video is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit generate_image_to_video? +

Yes. Add a rate_limit block to the generate_image_to_video 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 generate_image_to_video completely? +

Set action: deny in the PolicyLayer policy for generate_image_to_video. 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 generate_image_to_video? +

generate_image_to_video 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 →