AI agents call get_server_settings to retrieve information from Macinput without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves safety configuration information from the server without modifying, executing, or destroying any data. It is purely informational and has no operational impact on the system. The low severity reflects that exposing server settings has minimal blast radius compared to tools like click_mouse or keyboard_key_down that can directly control the GUI.
From the tool's definition Tool name 'get_server_settings' and description 'Return the active safety-related server settings' indicate a retrieval operation with no side effects. The word 'Return' explicitly indicates a read-only query of configuration data.
Attacks that exploit this kind of access
Return the active safety-related server settings. It is categorised as a Read tool in the Macinput MCP Server, which means it retrieves data without modifying state.
Register the Macinput MCP server in PolicyLayer and add a rule for get_server_settings: 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 Macinput. Nothing to install.
get_server_settings 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_server_settings 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_server_settings. 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_server_settings is provided by the Macinput MCP server (sigma711/macinput). 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 →