inpaint_image · Bedrock Image MCP: Risk & Policy

WHAT IT DOES

What inpaint_image does on Bedrock Image

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

WHY IT NEEDS A POLICY

Why inpaint_image needs a policy

Inpainting modifies images by filling in or editing specific regions—a reversible write operation. It does not delete data irreversibly (not Destructive), execute arbitrary code (not Execute), or involve financial transactions. The blast radius is medium since an agent could generate misleading or inappropriate modified images, but changes can be undone or reverted.

From the tool's definition Tool name 'inpaint_image' indicates image modification; sibling tools include 'generate_image', 'outpaint_image', 'remove_object', and 'remove_background' which all modify images.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

inpaint_image Rate-limited

inpaint_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": {
    "inpaint_image": {
      "limits": [
        {
          "counter": "inpaint_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 Bedrock Image, so you can run agents against it safely.

FAQ

Questions about inpaint_image

What does the inpaint_image tool do? +

inpaint_image. It is categorised as a Write tool in the Bedrock Image MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on inpaint_image? +

Register the Bedrock Image MCP server in PolicyLayer and add a rule for inpaint_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 Bedrock Image. Nothing to install.

What risk level is inpaint_image? +

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

Can I rate-limit inpaint_image? +

Yes. Add a rate_limit block to the inpaint_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 inpaint_image completely? +

Set action: deny in the PolicyLayer policy for inpaint_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 inpaint_image? +

inpaint_image is provided by the Bedrock Image MCP server (kalleeh/bedrock-image-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.