AI agents call domain_info to retrieve information from Libvirt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
domain_info is a pure information-gathering tool that queries and returns metadata about virtual machine state and configuration. It performs no modifications, deletions, or command execution. The low severity reflects minimal blast radius—an agent querying domain information cannot damage infrastructure or data.
From the tool's definition Tool retrieves 'Detailed info about a single domain: state, CPU/RAM, disks, NICs, leased IPs, snapshots' with no indication of modification, deletion, or execution. The description contains only query verbs (info retrieval).
Attacks that exploit this kind of access
Detailed info about a single domain: state, CPU/RAM, disks, NICs, leased IPs, snapshots. It is categorised as a Read tool in the Libvirt MCP Server, which means it retrieves data without modifying state.
Register the Libvirt MCP server in PolicyLayer and add a rule for domain_info: 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 Libvirt. Nothing to install.
domain_info 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 domain_info 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 domain_info. 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.
domain_info is provided by the Libvirt MCP server (rzippert/libvirt-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 →