Delete a file or directory.
AI agents call delete_path to permanently remove resources in Vscode — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs destructive operations that cannot be undone. Deletion of files or directories is irreversible data loss. An AI agent with access to this tool could accidentally or maliciously delete critical source code, configuration files, build artifacts, or entire project directories. In a code editor context (VS Code/Cursor), this poses extreme risk to user work and system integrity.
From the tool's definition Tool name 'delete_path' combined with description 'Delete a file or directory' explicitly describes irreversible deletion of files or directories.
Attacks that exploit this kind of access
Delete a file or directory. It is categorised as a Destructive tool in the Vscode MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Vscode MCP server in PolicyLayer and add a rule for delete_path: 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 Vscode. Nothing to install.
delete_path 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_path 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_path. 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_path is provided by the Vscode MCP server (kloutdevs/vscode-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 →