Add watermarks to PDF documents. Supports both text and image watermarks. Priority: user text > user image > environment variable image > default text
AI agents use add_watermark to create or update resources in Doc Ops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Doc Ops environment.
The tool modifies existing documents by adding visual overlays (watermarks), which is a Write operation—it transforms data but remains reversible. Severity is medium because while watermarking itself is non-destructive, unauthorized watermarks could deface documents or claim false ownership, presenting moderate risk if misused by an agent.
From the tool's definition add_watermark modifies PDF documents by adding watermarks (text or image), which changes the document's content and appearance. This is a reversible modification—the watermark can be removed or the document re-processed.
Documented attack patterns abuse exactly the kind of access add_watermark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Doc Ops, and nothing reaches the server without passing your rules. This is the rule we recommend for add_watermark:
{
"version": "1",
"default": "deny",
"tools": {
"add_watermark": {
"limits": [
{
"counter": "add_watermark_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Add watermarks to PDF documents. Supports both text and image watermarks. Priority: user text > user image > environment variable image > default text. It is categorised as a Write tool in the Doc Ops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Doc Ops MCP server in PolicyLayer and add a rule for 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 Doc Ops. Nothing to install.
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 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 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.
add_watermark is provided by the Doc Ops MCP server (tele-ai/doc-ops-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Doc Ops tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 Doc Ops tools catalogued and risk-classified — across an index of 42,500+ MCP servers.