Cost alerts based on budget thresholds and spending patterns
AI agents call get_cost_alerts to retrieve information from Terragrunt GCP Tool MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports cost alert data based on existing thresholds and spending patterns. It performs no infrastructure modifications, does not execute deployments or scripts, and does not delete or create resources.
From the tool's definition Tool name 'get_cost_alerts' and description 'Cost alerts based on budget thresholds and spending patterns' indicate retrieval and analysis of cost information without modification.
Attacks that exploit this kind of access
Cost alerts based on budget thresholds and spending patterns. It is categorised as a Read tool in the Terragrunt GCP Tool MCP MCP Server, which means it retrieves data without modifying state.
Register the Terragrunt GCP Tool MCP server in PolicyLayer and add a rule for get_cost_alerts: 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 Terragrunt GCP Tool MCP. Nothing to install.
get_cost_alerts 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_cost_alerts 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_cost_alerts. 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_cost_alerts is provided by the Terragrunt GCP Tool MCP server (spolspol/terragrunt-gcp-tool-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 →