// MCP TOOL REFERENCE

tf_destroy

Destroy Terraform-managed infrastructure

Tears down entire infrastructure stacks

Part of the AWS MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

// WHEN AI AGENTS USE THIS TOOL

AI agents may call tf_destroy to permanently remove or destroy resources in AWS. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON TF_DESTROY

Without a policy, an AI agent could call tf_destroy in a loop, permanently destroying resources in AWS. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

aws.yaml

tools:
  tf_destroy:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full AWS policy for all 58 tools.

// DETAILS

Tool Name tf_destroy

Category Destructive

MCP Server AWS MCP Server

Risk Level Critical

// MORE AWS TOOLS

Destructive cancel_logs_insight_query Destructive delete_resource Execute call_aws Execute execute_log_insights_query Execute invoke_lambda Write create_resource Write create_table_from_csv Write manage_eks_stacks

View all 58 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like tf_destroy have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_threat AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

tf_destroy is one of the critical-risk operations in AWS. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the tf_destroy tool do? +

Destroy Terraform-managed infrastructure. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on tf_destroy? +

Add a rule in your Intercept YAML policy under the tools section for tf_destroy. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS MCP server.

What risk level is tf_destroy? +

tf_destroy is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit tf_destroy? +

Yes. Add a rate_limit block to the tf_destroy rule in your Intercept 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.

How do I block tf_destroy completely? +

Set action: deny in the Intercept policy for tf_destroy. 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.

What MCP server provides tf_destroy? +

tf_destroy is provided by the AWS MCP server (@awslabs/mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

tf_destroy

Let agents act without letting them run wild.