ssh_download
AI agents call ssh_download to retrieve information from Mcp Ssh Live without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool downloads files from remote SSH hosts via SFTP, which is a read operation that retrieves data without modifying or deleting it. Severity is medium rather than low because downloaded files could expose sensitive data if an agent targets the wrong host or credentials, and the tool operates in a remote execution context where misuse could access confidential systems.
From the tool's definition Tool name 'ssh_download' and server context describing 'SFTP file transfer' capability indicate retrieval of remote files.
Attacks that exploit this kind of access
ssh_download. It is categorised as a Read tool in the Mcp Ssh Live MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh Live 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 Ssh Live. 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 Ssh Live MCP server (pmboxbiz/mcp-ssh-live). 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 →