Delete a worksheet from a workbook
AI agents call delete_worksheet to permanently remove resources in Excel — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of worksheet data cannot be undone through normal tool operations and represents permanent loss of information. This is more severe than Write (reversible modifications) and constitutes a Destructive action. High severity due to potential data loss, though blast radius is somewhat limited to a single worksheet rather than an entire workbook or system.
From the tool's definition Tool name is 'delete_worksheet' and description states 'Delete a worksheet from a workbook'. The verb 'delete' combined with removal of worksheet data is irreversible.
Attacks that exploit this kind of access
Delete a worksheet from a workbook. It is categorised as a Destructive tool in the Excel MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Excel MCP server in PolicyLayer and add a rule for delete_worksheet: 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 Excel. Nothing to install.
delete_worksheet 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_worksheet 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_worksheet. 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_worksheet is provided by the Excel MCP server (shmaxi/excel-mcp-server-node). 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 →