Medium Risk

resize

resize

How to control resize ↓

AI agents use resize to create or update resources in πŸͺ„ ImageSorcery MCP β€” usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your πŸͺ„ ImageSorcery MCP environment.

Medium Risk

The tool 'resize' on an image manipulation server creates or modifies image data reversibly. Resizing an image is a Write operationβ€”it transforms the image but does not delete it, and the change can be undone by resizing again.

From the tool's definition Tool name is 'resize' which modifies image dimensions. Description is empty, limiting direct evidence.

Documented attack patterns abuse exactly the kind of access resize gives an agent:

PolicyLayer is an MCP gateway β€” it sits between your AI agents and πŸͺ„ ImageSorcery MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for resize:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "resize": {
      "limits": [
        {
          "counter": "resize_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

resize stays usable, but capped β€” 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.

  1. Create a free account and register πŸͺ„ ImageSorcery MCP β€” nothing to install.
  2. Add this policy β€” paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the resize tool do? +

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

How do I enforce a policy on resize? +

Register the πŸͺ„ ImageSorcery MCP server in PolicyLayer and add a rule for resize: 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 πŸͺ„ ImageSorcery MCP. Nothing to install.

What risk level is resize? +

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

Can I rate-limit resize? +

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

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

resize is provided by the πŸͺ„ ImageSorcery MCP server (sunriseapps/imagesorcery-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every πŸͺ„ ImageSorcery MCP tool call.

Deterministic rules across all 17 πŸͺ„ ImageSorcery MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

17 πŸͺ„ ImageSorcery MCP tools catalogued and risk-classified β€” across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.