Delete a command-usage record by its id.
AI agents call delete_command_tool to permanently remove resources in Mcp Commands — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes historical records from the PostgreSQL database that tracks AI command usage. Deletion is irreversible; once a command-usage record is removed, it cannot be recovered without database restoration. The blast radius is high: a compromised AI agent could systematically erase audit trails, hiding command history and execution contexts.
From the tool's definition Tool name is 'delete_command_tool' and description explicitly states 'Delete a command-usage record by its id' — the word 'Delete' combined with permanent removal of a database record indicates an irreversible action.
Attacks that exploit this kind of access
Delete a command-usage record by its id. It is categorised as a Destructive tool in the Mcp Commands MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Commands MCP server in PolicyLayer and add a rule for delete_command_tool: 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 Mcp Commands. Nothing to install.
delete_command_tool 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_command_tool 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_command_tool. 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_command_tool is provided by the Mcp Commands MCP server (puemmth/mcp-commands). 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 →