MCP Tool Reference Critical Risk

tf_destroy

Destroy infrastructure

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

awslabs/mcp Destructive

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 55 tools.

DETAILS

Tool Name

tf_destroy

Category

Destructive

MCP Server

AWS MCP Servers

Risk Level

Critical

MORE AWS TOOLS

View all 55 tools →

SIMILAR DESTRUCTIVE TOOLS ON OTHER SERVERS

RELATED READING

FREQUENTLY ASKED QUESTIONS

What does the tf_destroy tool do?

Destroy infrastructure. It is categorised as a Destructive tool in the AWS MCP Servers, 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.

ENFORCE POLICIES ON AWS

Open source. One binary. Zero dependencies.