Manage Azure Virtual Machines — list, show, start, stop, deallocate, restart, delete.
AI agents call az_vm to permanently remove resources in RedisNexus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete action cannot be undone and results in permanent loss of infrastructure. Even though the tool also includes reversible operations (start, stop, restart, deallocate), the presence of delete capability places it in the Destructive category per the severity hierarchy. The impact on production systems could be catastrophic, justifying critical severity.
From the tool's definition Tool description explicitly includes 'delete' as a capability for Azure Virtual Machines, alongside start, stop, deallocate, and restart operations. Delete operations are irreversible.
Attacks that exploit this kind of access
Manage Azure Virtual Machines — list, show, start, stop, deallocate, restart, delete. It is categorised as a Destructive tool in the RedisNexus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RedisNexus MCP server in PolicyLayer and add a rule for az_vm: 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 RedisNexus. Nothing to install.
az_vm 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 az_vm 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 az_vm. 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.
az_vm is provided by the RedisNexus MCP server (rajkumar-madhu/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 →