AI agents call ftp_disk_space 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 disk space information from a remote server without modifying, deleting, or executing any operations. It is a passive information-gathering function. While it is restricted to SFTP connections, this is a security constraint rather than a category indicator. The blast radius of misuse is minimal—an agent querying disk space causes no damage or unintended state changes.
From the tool's definition Tool name is 'ftp_disk_space' and description states 'Query the remote server for available disk space.' The verb 'query' and the informational nature of disk space reporting indicate a read-only operation with no side effects.
Attacks that exploit this kind of access
Query the remote server for available disk space. CRITICAL: Only available on SFTP connections. 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_disk_space: 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_disk_space 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_disk_space 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_disk_space. 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_disk_space 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 →