AI agents use restore_from_trash to create or update resources in Yadisk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yadisk environment.
This tool performs a reversible modification: it restores deleted files/folders, changing their location and status but not destroying data. While restoration is a form of write operation, it is not destructive (the data was already in trash awaiting permanent deletion).
From the tool's definition Tool name is 'restore_from_trash' and description states it 'Restore[s] a file or folder from Trash.' This is a write operation that modifies the state of files by moving them from a deleted/trash state back to an active state.
Attacks that exploit this kind of access
Restore a file or folder from Trash. It is categorised as a Write tool in the Yadisk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yadisk MCP server in PolicyLayer and add a rule for restore_from_trash: 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.
restore_from_trash is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the restore_from_trash 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 restore_from_trash. 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.
restore_from_trash 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 →