Download a file from the remote host via SFTP.
AI agents call ssh_download to retrieve information from MCP Remote Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While the tool itself performs a read operation (no data modification), the severity is elevated to 'medium' rather than 'low' because: (1) it accesses remote systems that may contain sensitive configuration, credentials, or private data on embedded devices/IoT systems; (2) combined with the server's broad remote access capabilities, an agent could exfiltrate proprietary firmware, keys, or system secrets; (3) the…
From the tool's definition Tool name is 'ssh_download' and description states 'Download a file from the remote host via SFTP.' This is a retrieval operation that fetches data from a remote system without modifying it.
Attacks that exploit this kind of access
Download a file from the remote host via SFTP. It is categorised as a Read tool in the MCP Remote Access MCP Server, which means it retrieves data without modifying state.
Register the MCP Remote Access MCP server in PolicyLayer and add a rule for ssh_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 MCP Remote Access. Nothing to install.
ssh_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 ssh_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 ssh_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.
ssh_download is provided by the MCP Remote Access MCP server (rfingadam/mcp-remote-access). 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 →