Delete files or directories (permanent removal)
AI agents call delete_files to permanently remove resources in System Information MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes or overwrites data without the ability to undo the operation, meeting the definition of Destructive. Although the server description mentions 'built-in safety guards to prevent operations on critical system directories', the tool itself performs permanent deletion.
From the tool's definition Tool name is 'delete_files' with description 'Delete files or directories (permanent removal)'. The explicit use of 'permanent removal' confirms irreversible data loss.
Attacks that exploit this kind of access
Delete files or directories (permanent removal). It is categorised as a Destructive tool in the System Information MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the System Information MCP Server MCP server in PolicyLayer and add a rule for delete_files: 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 System Information MCP Server. Nothing to install.
delete_files 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_files 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_files. 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_files is provided by the System Information MCP Server MCP server (markolive1501/mcp). 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 →