gcp_compute_stop_instance
Stop a running VM instance
This record as markdown: /tools/ahmedselimmansor-ctrl-gcp-mcp-server/gcp-compute-stop-instance.md
What gcp_compute_stop_instance does on GCP MCP Server
AI agents invoke gcp_compute_stop_instance to trigger actions in GCP MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why gcp_compute_stop_instance is rated High
Stopping a VM instance is an Execute action—it runs an operation that changes system state (VM transitions from running to stopped), but is reversible (the instance can be restarted). It has significant blast radius in a production environment (service disruption, downtime), but does not delete data or move funds, so it does not qualify as Destructive or Financial.
From the tool's definition Tool name 'gcp_compute_stop_instance' and description 'Stop a running VM instance' indicate the tool triggers an external operation (stopping a VM) whose effects depend on which instance is targeted as an argument.
Attacks that exploit this kind of access
The rule that runs gcp_compute_stop_instance safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GCP MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gcp_compute_stop_instance, this is the rule to start with:
gcp_compute_stop_instance stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GCP MCP Server, apply this rule, and every gcp_compute_stop_instance call is checked against it from then on.
Questions about gcp_compute_stop_instance
Stop a running VM instance. It is categorised as a Execute tool in the GCP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GCP MCP Server MCP server in PolicyLayer and add a rule for gcp_compute_stop_instance: 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 GCP MCP Server. Nothing to install.
gcp_compute_stop_instance is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the gcp_compute_stop_instance 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_stop_instance. 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_stop_instance is provided by the GCP MCP Server MCP server (ahmedselimmansor-ctrl/gcp_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GCP MCP Server, and thousands of servers like it.
Across the catalogue