AI agents call get_status to retrieve information from Poof without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves terminal status information without side effects. Despite the server's overall dangerous capability (sending keystrokes, executing commands via Terminal.app), this specific tool is purely informational and safe when used in isolation. It belongs in the Read category with low severity due to its passive nature.
From the tool's definition Tool name 'get_status' and description 'Get terminal status' indicate a query operation that retrieves information about terminal state without modification. This aligns with the server's capability to 'capture screen output in real-time' as a read operation.
Attacks that exploit this kind of access
Get terminal status. It is categorised as a Read tool in the Poof MCP Server, which means it retrieves data without modifying state.
Register the Poof 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 Poof. 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 Poof MCP server (mattapperson/poof-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 →