Generate a Terraform resource following organization standards and security defaults
AI agents use generate_resource to create or update resources in Tf Dialect — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tf Dialect environment.
The tool creates new Terraform resource code which represents a write operation against IaC definitions. While the actual infrastructure changes only occur when Terraform apply is run (external to this tool), the tool itself generates code that will instruct infrastructure changes.
From the tool's definition Tool generates Terraform resources that follow organizational standards and security defaults, creating Infrastructure as Code artifacts that will modify cloud infrastructure configurations
Attacks that exploit this kind of access
Generate a Terraform resource following organization standards and security defaults. It is categorised as a Write tool in the Tf Dialect MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tf Dialect MCP server in PolicyLayer and add a rule for generate_resource: 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 Tf Dialect. Nothing to install.
generate_resource is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_resource 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 generate_resource. 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.
generate_resource is provided by the Tf Dialect MCP server (utpaljaynadiger/tf-dialect). 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 →