AI agents call ssh_get_command_status to retrieve information from Ssh Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the status and output of a previously executed command. It does not execute new commands, modify state, delete data, or commit financial actions. It is purely informational—retrieving state about an already-running or completed async command. The low severity reflects minimal blast radius: misuse would only expose command outputs that have already executed.
From the tool's definition The tool name is 'ssh_get_command_status' and the description translates to 'Get asynchronous command status and latest output'. The verb 'get' and the focus on retrieving status/output indicates a read-only operation with no side effects.
Attacks that exploit this kind of access
获取异步命令状态和最新输出. It is categorised as a Read tool in the Ssh Agent MCP Server, which means it retrieves data without modifying state.
Register the Ssh Agent MCP server in PolicyLayer and add a rule for ssh_get_command_status: 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 Agent. Nothing to install.
ssh_get_command_status 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_get_command_status 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_get_command_status. 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_get_command_status is provided by the Ssh Agent MCP server (zhijun/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 →