AI agents call getSystemInfo to retrieve information from Shell MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a Read operation—it queries and retrieves data without side effects. However, severity is elevated to 'high' rather than 'low' because system information (OS details, resource capacity, installed software, network config, process lists, etc.) is sensitive reconnaissance data that could enable privilege escalation, lateral movement, or targeted attacks if exposed to an untrusted AI agent.
From the tool's definition Tool name 'getSystemInfo' and description indicate it 'Retrieve[s] comprehensive system information about the host machine' with no modification or execution capability.
Attacks that exploit this kind of access
Retrieve comprehensive system information about the host machine. It is categorised as a Read tool in the Shell MCP MCP Server, which means it retrieves data without modifying state.
Register the Shell MCP server in PolicyLayer and add a rule for getSystemInfo: 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 Shell MCP. Nothing to install.
getSystemInfo 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 getSystemInfo 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 getSystemInfo. 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.
getSystemInfo is provided by the Shell MCP server (lucivuc/shell-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 →