image_generation · Deerflow Kinthai MCP: Risk & Policy

WHAT IT DOES

What image_generation does on Deerflow Kinthai

AI agents invoke image_generation to trigger actions in Deerflow Kinthai. 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 image_generation needs a policy

The tool triggers an external AI image generation operation based on user-provided text input. This is an external computation/generation action whose output depends on arguments, fitting the Execute category. It does not merely read existing data, nor does it write to a user-controlled data store in a reversible way — it invokes an AI model pipeline.

From the tool's definition 'Generate AI images based on a text description. Returns an image file.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

image_generation Rate-limited

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": {
    "image_generation": {
      "limits": [
        {
          "counter": "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 Deerflow Kinthai, so you can run agents against it safely.

FAQ

Questions about image_generation

What does the image_generation tool do? +

Generate AI images based on a text description. Returns an image file. It is categorised as a Execute tool in the Deerflow Kinthai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on image_generation? +

Register the Deerflow Kinthai MCP server in PolicyLayer and add a rule for 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 Deerflow Kinthai. Nothing to install.

What risk level is image_generation? +

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

Can I rate-limit image_generation? +

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

Set action: deny in the PolicyLayer policy for 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 image_generation? +

image_generation is provided by the Deerflow Kinthai MCP server (kinthaiofficial/mcp-server-deerflow-kinthai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.