Delete a file or folder.
AI agents call delete to permanently remove resources in Yadisk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete operation permanently removes files or folders, which cannot be undone. This matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone.' While the severity is high rather than critical because it operates on user data rather than system infrastructure, the irreversible nature of deletion and potential for an AI agent to mistakenly delete…
From the tool's definition Tool name is 'delete' and description explicitly states 'Delete a file or folder.' This is an irreversible operation that removes data from Yandex Disk.
Attacks that exploit this kind of access
Delete a file or folder. It is categorised as a Destructive tool in the Yadisk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Yadisk MCP server in PolicyLayer and add a rule for delete: 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 Yadisk. Nothing to install.
delete 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 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. 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 is provided by the Yadisk MCP server (patr56/yadisk-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 →