AI agents call ftp_search 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.
The ftp_search tool only searches and retrieves metadata about files and their contents. It does not create, modify, delete, or execute anything. The blast radius of misuse is minimal—an attacker could discover sensitive files or code patterns, but cannot alter or destroy data. This is a classic Read operation with low severity.
From the tool's definition Tool description states 'Advanced remote file search' with capabilities to 'find files by name', 'extension', or 'content regex'.
Attacks that exploit this kind of access
Advanced remote file search. Supports finding files by name (wildcards), extension, or content regex (grep-like). Use this to find specific code patterns across the remote workspace. 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_search: 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_search 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_search 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_search. 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_search 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 →