AI agents call ftp_exists to retrieve information from Ftp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about whether a file or folder exists on a remote FTP/SFTP server without modifying, deleting, or executing anything. It is purely informational and suitable for conditional logic workflows. No side effects or data mutations occur. This is a straightforward Read category operation with low severity due to its limited scope and non-destructive nature.
From the tool's definition Tool description states 'Check for the existence of a file or folder without performing heavy file operations.' The verb 'check' and explicit statement that no heavy operations are performed indicates a lightweight read-only query operation.
Attacks that exploit this kind of access
Check for the existence of a file or folder without performing heavy file operations. Use this for conditional logic workflows. It is categorised as a Read tool in the Ftp MCP Server, which means it retrieves data without modifying state.
Register the Ftp MCP server in PolicyLayer and add a rule for ftp_exists: 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_exists is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ftp_exists 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_exists. 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_exists 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 →