quarantine_host
AI agents call quarantine_host to permanently remove resources in Velociraptor MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Quarantining a host is a severe, potentially irreversible network isolation action that cuts off a machine from the network. In incident response contexts, this typically involves applying firewall rules or network isolation that can disrupt services and operations across entire systems.
From the tool's definition Tool name 'quarantine_host' on a digital forensics/incident response server (Velociraptor MCP). Sibling tools include 'kill_process', 'hunt_across_fleet', 'remediation actions' mentioned in server description.
Attacks that exploit this kind of access
quarantine_host. It is categorised as a Destructive tool in the Velociraptor MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Velociraptor MCP Server MCP server in PolicyLayer and add a rule for quarantine_host: 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 Velociraptor MCP Server. Nothing to install.
quarantine_host is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the quarantine_host 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 quarantine_host. 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.
quarantine_host is provided by the Velociraptor MCP Server MCP server (snoe-findley/mcp-velociraptor). 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 →