AI agents use insert_watermark to create or update resources in Docx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docx environment.
Inserting a watermark modifies document structure and appearance but does not destroy data or execute arbitrary code. It is a reversible write operation consistent with the server's editing capabilities. Severity is medium because while watermarks can alter document appearance and metadata, they do not cause data loss, financial impact, or arbitrary execution.
From the tool's definition Tool name 'insert_watermark' indicates creation/modification of document content. Server description states it enables 'editing...Microsoft Word documents' and 'precise OOXML-level document manipulation.' Watermarks are reversible visual elements added to…
Documented attack patterns abuse exactly the kind of access insert_watermark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for insert_watermark:
{
"version": "1",
"default": "deny",
"tools": {
"insert_watermark": {
"limits": [
{
"counter": "insert_watermark_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}insert_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.
insert_watermark. It is categorised as a Write tool in the Docx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docx MCP server in PolicyLayer and add a rule for insert_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 Docx. Nothing to install.
insert_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 insert_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 insert_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.
insert_watermark is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Docx, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
219 Docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.