List hosts that agents are running on
AI agents call empire_hosts to retrieve information from PowerShell Empire MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about compromised or monitored hosts without modifying or executing actions. It is fundamentally a Read operation. However, severity is High because the information disclosed reveals active attacker infrastructure and compromised system inventory, which is highly sensitive security-relevant data in the context of a red-team/penetration-testing framework like Empire.
From the tool's definition 'List hosts that agents are running on' — retrieves information about systems where Empire agents are deployed.
Attacks that exploit this kind of access
List hosts that agents are running on. It is categorised as a Read tool in the PowerShell Empire MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PowerShell Empire MCP Server MCP server in PolicyLayer and add a rule for empire_hosts: 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 PowerShell Empire MCP Server. Nothing to install.
empire_hosts 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 empire_hosts 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 empire_hosts. 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.
empire_hosts is provided by the PowerShell Empire MCP Server MCP server (schwarztim/sec-powershell-empire-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 →