watermark_image · SVG Canvas MCP: Risk & Policy

WHAT IT DOES

What watermark_image does on SVG Canvas MCP

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

WHY IT NEEDS A POLICY

Why watermark_image needs a policy

This tool creates or modifies SVG canvas data by applying a watermark, which is a reversible operation (the watermark can be removed or the canvas reset). It does not execute arbitrary code, delete data, or cause financial impact. The modification is confined to the current canvas state and does not affect external systems.

From the tool's definition Tool name 'watermark_image' and description indicating it 'applies image watermark to current canvas' — this modifies the canvas content by adding a watermark overlay

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watermark_image Rate-limited

watermark_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": {
    "watermark_image": {
      "limits": [
        {
          "counter": "watermark_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 SVG Canvas MCP, so you can run agents against it safely.

FAQ

Questions about watermark_image

What does the watermark_image tool do? +

이미지 워터마크를 현재 캔버스에 적용합니다. It is categorised as a Write tool in the SVG Canvas 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 watermark_image? +

Register the SVG Canvas MCP server in PolicyLayer and add a rule for watermark_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 SVG Canvas MCP. Nothing to install.

What risk level is watermark_image? +

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

Can I rate-limit watermark_image? +

Yes. Add a rate_limit block to the watermark_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 watermark_image completely? +

Set action: deny in the PolicyLayer policy for watermark_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 watermark_image? +

watermark_image is provided by the SVG Canvas MCP server (kim62210/svg-canvas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.