add_text_watermark · Mcp Watermark MCP: Risk & Policy

WHAT IT DOES

What add_text_watermark does on Mcp Watermark

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

WHY IT NEEDS A POLICY

Why add_text_watermark needs a policy

This tool modifies PDF documents by adding watermarks to them. The modification is reversible (watermarks can be removed or the original document restored), so it falls under Write rather than Destructive. Severity is medium because while the PDF is altered, the core content remains intact and the change is non-destructive. The confidence is high because the function clearly describes a write/modification operation.

From the tool's definition Tool description states it will 'Add a diagonal text watermark to all pages in a PDF file,' indicating modification of an existing PDF document.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_text_watermark Rate-limited

add_text_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": {
    "add_text_watermark": {
      "limits": [
        {
          "counter": "add_text_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 Mcp Watermark, so you can run agents against it safely.

FAQ

Questions about add_text_watermark

What does the add_text_watermark tool do? +

Add a diagonal text watermark to all pages in a PDF file. It is categorised as a Write tool in the Mcp Watermark MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_text_watermark? +

Register the Mcp Watermark MCP server in PolicyLayer and add a rule for add_text_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 Mcp Watermark. Nothing to install.

What risk level is add_text_watermark? +

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

Can I rate-limit add_text_watermark? +

Yes. Add a rate_limit block to the add_text_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 add_text_watermark completely? +

Set action: deny in the PolicyLayer policy for add_text_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 add_text_watermark? +

add_text_watermark is provided by the Mcp Watermark MCP server (xecho-dev/mcp-watermark). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.