AI agents use copy 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.
Copying creates or duplicates data in a new location but does not delete the original or irreversibly alter existing data. The operation is reversible (the copy can be deleted). While it modifies the filesystem structure, it falls short of Destructive (which requires irreversible deletion) and Execute (which requires code/command execution).
From the tool's definition Tool description states 'Copy a file or folder to a new location.' The action creates a new copy of data at a destination, which is a reversible modification operation characteristic of Write category.
Attacks that exploit this kind of access
Copy a file or folder to a new location. 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 copy: 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.
copy 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 copy 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 copy. 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.
copy 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 →