tool_transform_image · Open Google Image Generator MCP

WHAT IT DOES

What tool_transform_image does on Open Google Image Generator MCP

AI agents invoke tool_transform_image to trigger actions in Open Google Image Generator MCP. 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 tool_transform_image needs a policy

This tool executes generative AI model inference (Gemini) with free-form user inputs to produce modified images. While the transformation itself is reversible (not Destructive), the 'Execute' category applies because it triggers external operations (model inference) whose output depends on arbitrary arguments (the text prompt).

From the tool's definition 'Free-form' transformation that accepts image and text inputs and produces modified images via Gemini multimodal models; execution of generative AI models with arbitrary user-supplied text prompts to transform images.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tool_transform_image Rate-limited

tool_transform_image 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": {
    "tool_transform_image": {
      "limits": [
        {
          "counter": "tool_transform_image_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 Open Google Image Generator MCP, so you can run agents against it safely.

FAQ

Questions about tool_transform_image

What does the tool_transform_image tool do? +

Free-form 'image + text -> image' transformation via Gemini multimodal models. It is categorised as a Execute tool in the Open Google Image Generator MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tool_transform_image? +

Register the Open Google Image Generator MCP server in PolicyLayer and add a rule for tool_transform_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 Open Google Image Generator MCP. Nothing to install.

What risk level is tool_transform_image? +

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

Can I rate-limit tool_transform_image? +

Yes. Add a rate_limit block to the tool_transform_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 tool_transform_image completely? +

Set action: deny in the PolicyLayer policy for tool_transform_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 tool_transform_image? +

tool_transform_image is provided by the Open Google Image Generator MCP server (miracorhan/opengoogleimagegeneratormcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.