generate-image · MCP-Claude MCP: Risk & Policy

WHAT IT DOES

What generate-image does on MCP-Claude

AI agents invoke generate-image to trigger actions in MCP-Claude. 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 generate-image needs a policy

This tool invokes an external AI service (Replicate) to generate images, which constitutes triggering an external operation. It may incur costs depending on the Replicate account configuration, but without explicit evidence of billing/payment handling, Execute is the most appropriate category. Misuse could result in unwanted API calls, resource consumption, or generation of inappropriate content.

From the tool's definition "Generate an image using Replicate" — triggers an external operation on the Replicate platform

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate-image Rate-limited

generate-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": {
    "generate-image": {
      "limits": [
        {
          "counter": "generate-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 MCP-Claude, so you can run agents against it safely.

FAQ

Questions about generate-image

What does the generate-image tool do? +

Generate an image using Replicate. It is categorised as a Execute tool in the MCP-Claude 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? +

Register the MCP-Claude MCP server in PolicyLayer and add a rule for generate-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 MCP-Claude. Nothing to install.

What risk level is generate-image? +

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

Can I rate-limit generate-image? +

Yes. Add a rate_limit block to the generate-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-image completely? +

Set action: deny in the PolicyLayer policy for generate-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-image? +

generate-image is provided by the MCP-Claude MCP server (virajsamarasinghe/mcp-claude). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.