AI agents call ftp_probe_capabilities 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 performs reconnaissance of remote filesystem capabilities (chmod availability, symlink support, disk space querying) without modifying any data or executing operations. It is analogous to diagnostic queries like 'uname', 'ls -l', or capability detection. No side effects or state changes occur.
From the tool's definition Tool description states it 'scan[s] the remote server to determine supported filesystem features' and is 'helpful for troubleshooting capabilities'.
Attacks that exploit this kind of access
Scan the remote server to determine supported filesystem features (e.g., chmod availability, symlink support, disk space querying). Helpful for troubleshooting capabilities. 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_probe_capabilities: 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_probe_capabilities 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_probe_capabilities 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_probe_capabilities. 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_probe_capabilities 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 →