Copy file or directory.
AI agents use cp to create or update resources in MCP File System Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP File System Server environment.
Copying a file or directory creates new data at the destination path. This is a reversible Write operation (the copy can be deleted). However, it could overwrite an existing file at the destination, which raises the severity slightly. It does not delete the source, so it is not Destructive. Severity is medium because misuse could silently overwrite important files at the destination path.
From the tool's definition 'Copy file or directory' — creates a new copy of existing data without removing the original
Attacks that exploit this kind of access
Copy file or directory. It is categorised as a Write tool in the MCP File System Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP File System Server MCP server in PolicyLayer and add a rule for cp: 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 MCP File System Server. Nothing to install.
cp 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 cp 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 cp. 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.
cp is provided by the MCP File System Server MCP server (kvas-it/mcp-server-fs). 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 →