delete_action
AI agents call delete_action to permanently remove resources in Restcsv — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Delete operations are inherently destructive and irreversible. Without description text, we rely on the clear semantic meaning of 'delete' combined with the action management context (evidenced by sibling tools like create_action and list_actions). Even without full documentation, deletion cannot be undone, making this high-severity and warranting the Destructive category over Execute.
From the tool's definition Tool named 'delete_action' with no descriptive text; contextually part of a RestCSV action management system where 'delete' operations are irreversible.
Attacks that exploit this kind of access
delete_action. It is categorised as a Destructive tool in the Restcsv MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Restcsv MCP server in PolicyLayer and add a rule for delete_action: 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 Restcsv. Nothing to install.
delete_action 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_action 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_action. 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_action is provided by the Restcsv MCP server (restcsv-mcp-server). 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 →