Delete a Fly.io machine. Permanently removes a Fly machine that was used for Proctor exam execution. Use this to clean up machines that are no longer needed. Returns: - success: boolean indicating if the machine was deleted Use cases: - Clean up machines after exam completion - Remove stuck or fa...
AI agents call destroy_machine to permanently remove resources in Langfuse Observability — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes cloud infrastructure (a Fly.io machine). It cannot be undone and terminates running processes. This is a destructive action with significant blast radius if misused by an AI agent—it could delete production machines, interrupt services, or cause data loss if machines contain persistent state.
From the tool's definition Tool name is 'destroy_machine' and description explicitly states 'Permanently removes a Fly.io machine' and 'This action is irreversible'. The tool deletes infrastructure without the ability to undo the operation.
Attacks that exploit this kind of access
Delete a Fly.io machine. Permanently removes a Fly machine that was used for Proctor exam execution. Use this to clean up machines that are no longer needed. Returns: - success: boolean indicating if the machine was deleted Use cases: - Clean up machines after exam completion - Remove stuck or failed machines - Free up resources - Remove machines that are no longer needed Warning: - This action is irreversible - Any running processes on the machine will be terminated - Use cancel_exam first if there. It is categorised as a Destructive tool in the Langfuse Observability MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Langfuse Observability MCP server in PolicyLayer and add a rule for destroy_machine: 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 Langfuse Observability. Nothing to install.
destroy_machine is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the destroy_machine 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 destroy_machine. 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.
destroy_machine is provided by the Langfuse Observability MCP server (langfuse-observability-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 →