Delete a stream.
AI agents call npm_delete_stream to permanently remove resources in Nginx Manager — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion operations are irreversible and cannot be undone without external restoration. Deleting a stream in Nginx Proxy Manager removes network routing configuration, which could disrupt services if done in error. This is classified as Destructive rather than Write because the action cannot be reversed through the same API.
From the tool's definition Tool name 'npm_delete_stream' and description 'Delete a stream' indicate irreversible deletion of a stream configuration.
Attacks that exploit this kind of access
Delete a stream. It is categorised as a Destructive tool in the Nginx Manager MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nginx Manager MCP server in PolicyLayer and add a rule for npm_delete_stream: 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 Nginx Manager. Nothing to install.
npm_delete_stream 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 npm_delete_stream 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 npm_delete_stream. 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.
npm_delete_stream is provided by the Nginx Manager MCP server (kognar-ai/ngnix-manager-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 →