AI agents call remove_bookmark to permanently remove resources in Docx — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a bookmark is an irreversible deletion of a document element. While the paragraph content is preserved, the bookmark itself cannot be recovered without an undo operation, making this Destructive. Severity is medium since it affects a discrete named element rather than bulk document content.
From the tool's definition 'Remove a bookmark by name' — permanently removes a named bookmark from the document
Documented attack patterns abuse exactly the kind of access remove_bookmark 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 remove_bookmark:
{
"version": "1",
"default": "deny",
"hide": [
"remove_bookmark"
]
} remove_bookmark disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove a bookmark by name (keeps paragraph content). It is categorised as a Destructive tool in the Docx MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Docx MCP server in PolicyLayer and add a rule for remove_bookmark: 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.
remove_bookmark is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_bookmark 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 remove_bookmark. 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.
remove_bookmark 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.