generate_asset_image · Narrarium MCP: Risk & Policy

WHAT IT DOES

What generate_asset_image does on Narrarium

AI agents use generate_asset_image to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.

WHY IT NEEDS A POLICY

Why generate_asset_image needs a policy

This tool creates new image assets and modifies metadata in a structured repository. These are reversible write operations—generated images and their metadata can be edited or deleted later. The tool does not delete data (not Destructive), execute arbitrary code (not Execute), involve financial transactions (not Financial), or merely retrieve information (not Read).

From the tool's definition Tool description states it will 'Generate an image for a canonical subject, save it into the assets tree, and keep the asset prompt metadata in sync.' The key verbs are 'save' and 'keep...in sync,' indicating creation and modification of data (the generated…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_asset_image Rate-limited

generate_asset_image 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about generate_asset_image

What does the generate_asset_image tool do? +

Generate an image for a canonical subject, save it into the assets tree, and keep the asset prompt metadata in sync. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_asset_image? +

Register the Narrarium MCP server in PolicyLayer and add a rule for generate_asset_image: 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 Narrarium. Nothing to install.

What risk level is generate_asset_image? +

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

Can I rate-limit generate_asset_image? +

Yes. Add a rate_limit block to the generate_asset_image 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_asset_image completely? +

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

generate_asset_image is provided by the Narrarium MCP server (narrarium-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.