AI agents call resourceUsage to retrieve information from Terraform without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Alternative resource name field (fallback if resource not specified) |
provider | string | — | Provider name (e.g. 'aws') |
resource | string | — | Resource name (e.g. 'aws_instance') |
Parameters from the server's own tool schema.
This tool retrieves read-only information about Terraform resource usage examples and documentation. It does not create, modify, delete, or execute any infrastructure or code. It is analogous to consulting documentation or examples in the Terraform Registry, making it a Read category tool with minimal risk.
From the tool's definition Tool name 'resourceUsage' combined with description 'Get an example usage' indicates retrieval of documentation/examples. The verb 'Get' and the focus on retrieving 'example usage' and 'related resources' are query operations with no side effects.
Attacks that exploit this kind of access
Get an example usage of a Terraform resource and related resources. It is categorised as a Read tool in the Terraform MCP Server, which means it retrieves data without modifying state.
resourceUsage accepts 3 parameters: name, provider, resource. The full parameter table on this page comes from the server's own tool schema.
Register the Terraform MCP server in PolicyLayer and add a rule for resourceUsage: 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. Nothing to install.
resourceUsage 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 resourceUsage 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 resourceUsage. 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.
resourceUsage is provided by the Terraform MCP server (terraform-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 →