Manage GCP Compute Engine — list, describe, start, stop, delete instances, list disks.
AI agents call gcp_compute 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 tool permits deletion of GCP Compute Engine instances, which is an irreversible action that destroys infrastructure and can result in data loss. Although the tool also offers non-destructive operations (list, describe, start, stop), the presence of the delete capability elevates it to the Destructive category per the rule that severity is judged by the most severe applicable action.
From the tool's definition Tool description explicitly includes 'delete instances' and 'list disks', which are irreversible destructive operations. The capability to delete compute instances represents permanent removal of infrastructure and associated data.
Attacks that exploit this kind of access
Manage GCP Compute Engine — list, describe, start, stop, delete instances, list disks. 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 gcp_compute: 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.
gcp_compute 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 gcp_compute 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 gcp_compute. 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.
gcp_compute 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 →