AI agents call delete_header 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.
This tool permanently removes document structure (headers) which cannot be recovered without undo functionality at the application level. While the blast radius is somewhat contained (headers are document sections rather than entire documents), the irreversible nature of deletion places this in the Destructive category rather than Write.
From the tool's definition Tool name 'delete_header' with verb 'Delete' and description states 'Delete a header by location'; deletion of document headers is irreversible and cannot be undone through the tool's normal operation.
Documented attack patterns abuse exactly the kind of access delete_header 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 delete_header:
{
"version": "1",
"default": "deny",
"hide": [
"delete_header"
]
}delete_header 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.
Delete a header by location: default, first, or even. 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 delete_header: 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.
delete_header 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 delete_header 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 delete_header. 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.
delete_header 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.