Run infracost breakdown for a Terraform directory.
AI agents invoke run_infracost to trigger actions in Terraform Best Practices. 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.
This tool executes an external command (Infracost analysis) on Terraform infrastructure code. While ostensibly read-only in outcome (generates reports), it actively runs code/tools whose behavior depends on the supplied directory path and Terraform configuration contents.
From the tool's definition Tool name 'run_infracost' with description 'Run infracost breakdown for a Terraform directory' indicates execution of an external tool (Infracost) against infrastructure code.
Attacks that exploit this kind of access
Run infracost breakdown for a Terraform directory. It is categorised as a Execute tool in the Terraform Best Practices MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Terraform Best Practices MCP server in PolicyLayer and add a rule for run_infracost: 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 Terraform Best Practices. Nothing to install.
run_infracost 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 run_infracost 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 run_infracost. 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.
run_infracost is provided by the Terraform Best Practices MCP server (@downatthebottomofthemolehole/terraform-best-practices-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 →