Delete a CSV file (with backup if enabled).
AI agents call delete_csv to permanently remove resources in CSV MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes CSV files from the filesystem. Even though a backup option may exist, the primary action is irreversible deletion of data. This falls squarely into the Destructive category as it cannot be undone without restoration from backups external to the tool itself.
From the tool's definition Tool name is 'delete_csv' and description states 'Delete a CSV file', which explicitly performs irreversible deletion of data files.
Attacks that exploit this kind of access
Delete a CSV file (with backup if enabled). It is categorised as a Destructive tool in the CSV MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CSV MCP Server MCP server in PolicyLayer and add a rule for delete_csv: 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 CSV MCP Server. Nothing to install.
delete_csv 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_csv 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_csv. 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_csv is provided by the CSV MCP Server MCP server (novaai-innovation/csv-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 →