Close a specific connection.
AI agents call delete-connection to permanently remove resources in Rabbitmq — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a network connection is a destructive, non-reversible action. Any in-flight messages or work being done over that connection will be interrupted or lost. There is no 'undo' for a closed connection; the client must reconnect. Given the RabbitMQ context, forcibly closing a connection could disrupt active message consumers or producers, potentially causing message loss or service disruption.
From the tool's definition "Close a specific connection" — closing a connection is an irreversible action that immediately terminates an active client connection
Attacks that exploit this kind of access
Close a specific connection. It is categorised as a Destructive tool in the Rabbitmq MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for delete-connection: 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 Rabbitmq. Nothing to install.
delete-connection 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 delete-connection 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 delete-connection. 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.
delete-connection is provided by the Rabbitmq MCP server (rabbitmq-mcp). 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 →