AI agents call get-status to retrieve information from Ssh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs only information retrieval about system state. It does not create, modify, delete, or execute operations—it simply gathers and returns status data. The blast radius of misuse is minimal; an agent obtaining system status information poses no direct risk to system integrity or data. Therefore, it is classified as Read with low severity.
From the tool's definition Tool name 'get-status' and description 'Get comprehensive system status information from the remote server' indicates a read-only operation that retrieves and queries system metrics (OS, CPU, memory, disk, processes, services) with no modification of data.
Attacks that exploit this kind of access
Get comprehensive system status information from the remote server (OS, CPU, memory, disk, processes, services). It is categorised as a Read tool in the Ssh MCP Server, which means it retrieves data without modifying state.
Register the Ssh MCP server in PolicyLayer and add a rule for get-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. Nothing to install.
get-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 get-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 get-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.
get-status is provided by the Ssh MCP server (zachflint/ssh-mcp-server). 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 →