image_add_watermark · TSCodex MCP Images MCP: Risk & Policy

WHAT IT DOES

What image_add_watermark does on TSCodex MCP Images

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

WHY IT NEEDS A POLICY

Why image_add_watermark needs a policy

The tool creates or modifies an existing image by applying a watermark overlay. This is a reversible operation (the original image could be restored or the watermarked version deleted), making it Write rather than Destructive. The severity is medium because misuse could deface multiple images or apply inappropriate watermarks, but the operation remains reversible and does not delete data or execute arbitrary code.

From the tool's definition Tool description states 'Add watermark to image' with customizable positioning, size, and opacity. This modifies the image file by adding a watermark overlay.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

image_add_watermark Rate-limited

image_add_watermark 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": {
    "image_add_watermark": {
      "limits": [
        {
          "counter": "image_add_watermark_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 TSCodex MCP Images, so you can run agents against it safely.

FAQ

Questions about image_add_watermark

What does the image_add_watermark tool do? +

Add watermark to image. Supports text or image watermarks with customizable positioning, size, and opacity. All paths are relative to the project root. It is categorised as a Write tool in the TSCodex MCP Images MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on image_add_watermark? +

Register the TSCodex MCP Images MCP server in PolicyLayer and add a rule for image_add_watermark: 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 TSCodex MCP Images. Nothing to install.

What risk level is image_add_watermark? +

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

Can I rate-limit image_add_watermark? +

Yes. Add a rate_limit block to the image_add_watermark 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_add_watermark completely? +

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

image_add_watermark is provided by the TSCodex MCP Images MCP server (unbywyd/tscodex-mcp-images). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.