run_image_generation · Model Runner MCP: Risk & Policy

WHAT IT DOES

What run_image_generation does on Model Runner

AI agents invoke run_image_generation to trigger actions in Model Runner. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_image_generation needs a policy

This falls under Execute rather than Write because it triggers an external generative service whose effects are determined by the arguments passed. While image generation itself is not inherently destructive or financial, it invokes a remote AI service that consumes API credits/quota and produces artifacts whose creation cannot be reversed.

From the tool's definition Tool calls external API (DALL-E) to generate images based on text input; the tool's action produces side effects (image generation) that depend on the user-supplied prompt argument and cannot be undone.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_image_generation Rate-limited

run_image_generation 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Model Runner, so you can run agents against it safely.

FAQ

Questions about run_image_generation

What does the run_image_generation tool do? +

Generate an image from a text description using DALL-E. e.g., provider:. It is categorised as a Execute tool in the Model Runner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_image_generation? +

Register the Model Runner MCP server in PolicyLayer and add a rule for run_image_generation: 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 Model Runner. Nothing to install.

What risk level is run_image_generation? +

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

Can I rate-limit run_image_generation? +

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

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

run_image_generation is provided by the Model Runner MCP server (josephtandle/replicate-mcp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.