Download a file from the remote server via SFTP
AI agents call sftp_download to retrieve information from SSH MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While sftp_download is categorized as Read (retrieves data without side effects), the severity is medium rather than low because: (1) it can expose sensitive data from remote servers if an AI agent downloads confidential files without proper authorization checks, and (2) the broader SSH MCP Server context includes destructive and code-execution capabilities (ssh_exec, sftp_upload) that could compound risks if an…
From the tool's definition Tool name 'sftp_download' and description 'Download a file from the remote server via SFTP' indicate data retrieval with no modification or deletion of remote data.
Attacks that exploit this kind of access
Download a file from the remote server via SFTP. It is categorised as a Read tool in the SSH MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SSH MCP Server MCP server in PolicyLayer and add a rule for sftp_download: 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 SSH MCP Server. Nothing to install.
sftp_download 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 sftp_download 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 sftp_download. 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.
sftp_download is provided by the SSH MCP Server MCP server (kpanuragh/ssh-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 →