run_trivy · Terraform Best Practices MCP: Risk & Policy

WHAT IT DOES

What run_trivy does on Terraform Best Practices

AI agents invoke run_trivy 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.

WHY IT NEEDS A POLICY

Why run_trivy needs a policy

This tool triggers external command execution (Trivy scan) which is a computational operation with effects that depend on the Terraform code being scanned. While the immediate output is informational (security findings), the act of executing an external tool qualifies it as Execute category.

From the tool's definition Tool performs 'run_trivy' which executes an external security scanning tool (Trivy) against Terraform code. The description explicitly states it 'Run[s]' trivy, indicating active execution of a third-party scanning process rather than passive data retrieval.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_trivy Rate-limited

run_trivy 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_trivy": {
      "limits": [
        {
          "counter": "run_trivy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Terraform Best Practices, so you can run agents against it safely.

FAQ

Questions about run_trivy

What does the run_trivy tool do? +

Run trivy config scanning against Terraform code. 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.

How do I enforce a policy on run_trivy? +

Register the Terraform Best Practices MCP server in PolicyLayer and add a rule for run_trivy: 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.

What risk level is run_trivy? +

run_trivy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_trivy? +

Yes. Add a rate_limit block to the run_trivy 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.

How do I block run_trivy completely? +

Set action: deny in the PolicyLayer policy for run_trivy. 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.

What MCP server provides run_trivy? +

run_trivy 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.