Get Terraform outputs
AI agents call tf_output to retrieve information from Terraform MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Terraform outputs are read-only data exports that provide information about managed infrastructure (e.g., IP addresses, DNS names, resource IDs). This tool retrieves that data without executing, creating, modifying, or destroying infrastructure or state. It has minimal blast radius — an AI agent misusing it could only leak or misinterpret output values, not alter infrastructure or create financial obligations.
From the tool's definition Tool description states 'Get Terraform outputs' — a retrieval operation with no modification or destructive action. The verb 'Get' indicates querying/fetching data only.
Attacks that exploit this kind of access
Get Terraform outputs. It is categorised as a Read tool in the Terraform MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Terraform MCP Server MCP server in PolicyLayer and add a rule for tf_output: 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 MCP Server. Nothing to install.
tf_output 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 tf_output 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 tf_output. 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.
tf_output is provided by the Terraform MCP Server MCP server (mjrestivo16/mcp-terraform). 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 →