Add a text watermark to all or specific pages of a PDF.
AI agents use pdf_add_watermark to create or update resources in Mcp Pdf Utils — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Pdf Utils environment.
Adding a watermark modifies the PDF document's visual content in a reversible manner (the watermark can be removed or the original re-processed). This is a Write operation rather than Execute because it applies a predefined transformation to a file without running arbitrary code.
From the tool's definition Tool description states 'Add a text watermark to all or specific pages of a PDF' — this modifies PDF content by adding visual elements. Server description confirms it performs 'watermarking' as one of its PDF manipulation capabilities.
Attacks that exploit this kind of access
Add a text watermark to all or specific pages of a PDF. It is categorised as a Write tool in the Mcp Pdf Utils MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Pdf Utils MCP server in PolicyLayer and add a rule for pdf_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 Mcp Pdf Utils. Nothing to install.
pdf_add_watermark is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pdf_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.
Set action: deny in the PolicyLayer policy for pdf_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.
pdf_add_watermark is provided by the Mcp Pdf Utils MCP server (zekovdev/mcp-pdf-utils). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →