AI agents call get_instance to retrieve information from Gcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata and configuration details about a specific Compute Engine instance. It performs a read-only query operation with no side effects, capability to execute code, delete resources, or move funds. The blast radius of misuse is minimal—an attacker could enumerate instance details but cannot modify, destroy, or operate on infrastructure.
From the tool's definition Tool name 'get_instance' and description 'Get details for a single Compute Engine instance' indicate a retrieval operation with no modification or execution of resources.
Attacks that exploit this kind of access
Get details for a single Compute Engine instance. It is categorised as a Read tool in the Gcp MCP Server, which means it retrieves data without modifying state.
Register the Gcp MCP server in PolicyLayer and add a rule for get_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. Nothing to install.
get_instance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_instance is provided by the Gcp MCP server (lokimcpuniverse/gcp-mcp-server). 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 →