start_instance
Starts a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is DONE without any errors. To get details of the operation, use the get_zone_operation tool.
This record as markdown: /tools/com-googleapis-compute-mcp/start-instance.md
What start_instance does on Mcp
AI agents invoke start_instance to trigger actions in Mcp. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Required. Identifier. The instance name. |
zone | string | Yes | Required. The zone of the instance. |
project | string | Yes | Required. Project ID for this request. |
Parameters from the server's own tool schema.
Why start_instance is rated High
The tool executes an action (starting a VM instance) on external infrastructure. While not destructive (reversible via stop_instance), it meets the Execute category definition: 'runs code, shell commands, browser actions, or triggers external operations whose effects depend on arguments.' The high severity reflects that an agent could start numerous expensive compute resources, incurring unexpected costs and…
From the tool's definition Tool description states it 'Starts a Google Compute Engine virtual machine (VM) instance' and requires project, zone, and instance name.
Attacks that exploit this kind of access
The rule that runs start_instance safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_instance, this is the rule to start with:
start_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 Mcp, apply this rule, and every start_instance call is checked against it from then on.
Questions about start_instance
Starts a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is DONE without any errors. To get details of the operation, use the get_zone_operation tool. It is categorised as a Execute tool in the Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
start_instance accepts 3 parameters: name, zone, project. Required: name, zone, project. The full parameter table on this page comes from the server's own tool schema.
Register the MCP server in PolicyLayer and add a rule for start_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 Mcp. Nothing to install.
start_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 start_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 start_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.
start_instance is provided by the MCP server (https://compute.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on , and thousands of servers like it.
This server
Across the catalogue