AI agents call snapshot_list 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.
This tool queries and retrieves snapshot information from a domain without creating, modifying, deleting, or executing any operations. It is purely informational, fitting the Read category definition of 'retrieves or queries data; no side effects'. Low severity because misuse would only expose information about existing snapshots, not enable destructive or operational changes.
From the tool's definition Tool name is 'snapshot_list' and description states it 'List snapshots' — a retrieval operation with no modification or side effects. Returns metadata about snapshots (creation time, state, parent, description).
Attacks that exploit this kind of access
List snapshots of a domain with creation time, state, parent and description. 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 snapshot_list: 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.
snapshot_list 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 snapshot_list 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 snapshot_list. 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.
snapshot_list 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 →