AI agents use ftp_copy to create or update resources in Ftp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ftp environment.
ftp_copy performs file duplication on a remote server, which is a reversible modification operation (Write category). While it doesn't delete data, the blast radius is high because an AI agent could maliciously duplicate large files to consume disk space, duplicate sensitive files to unintended locations, or exhaust storage resources.
From the tool's definition Tool description states 'duplicate a file on the remote server' which creates a new copy of data. The tool modifies the remote filesystem by adding content (a duplicate file), making it a write operation.
Attacks that exploit this kind of access
Directly duplicate a file on the remote server without downloading and re-uploading. CRITICAL: Only supported on SFTP connections. It is categorised as a Write tool in the Ftp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ftp MCP server in PolicyLayer and add a rule for ftp_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 Ftp. Nothing to install.
ftp_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 ftp_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 ftp_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.
ftp_copy is provided by the Ftp MCP server (kynlos/ftp-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 →