Write a Terraform file
AI agents use tf_write_file to create or update resources in Terraform MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Terraform MCP Server environment.
This tool creates or modifies Terraform configuration files, which is a reversible write operation. While the modification itself is not destructive, it can cascade into destructive infrastructure changes when combined with tf_apply or tf_destroy.
From the tool's definition Tool name 'tf_write_file' and description 'Write a Terraform file' explicitly indicate file creation or modification of Terraform configuration.
Attacks that exploit this kind of access
Write a Terraform file. It is categorised as a Write tool in the Terraform MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Terraform MCP Server MCP server in PolicyLayer and add a rule for tf_write_file: 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_write_file 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 tf_write_file 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_write_file. 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_write_file 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 →