AI agents call iac_terraform_state to retrieve information from Infra Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves Terraform state information for inspection purposes. While it does not modify, delete, or execute operations, the high severity reflects that Terraform state files typically contain sensitive data including database passwords, API keys, private IP addresses, and other credentials. Exposure of this data to an untrustworthy AI agent could lead to credential compromise and lateral movement attacks.
From the tool's definition Tool name 'iac_terraform_state' and description 'Show the current Terraform state in JSON format' indicate a read-only query operation that retrieves and displays data without modifying infrastructure.
Attacks that exploit this kind of access
Show the current Terraform state in JSON format. It is categorised as a Read tool in the Infra Ops MCP Server, which means it retrieves data without modifying state.
Register the Infra Ops MCP server in PolicyLayer and add a rule for iac_terraform_state: 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 Infra Ops. Nothing to install.
iac_terraform_state 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 iac_terraform_state 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 iac_terraform_state. 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.
iac_terraform_state is provided by the Infra Ops MCP server (skyvanguard/infra-ops-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 →