AI agents use unprotect-vhost to create or update resources in Rabbitmq — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rabbitmq environment.
This tool modifies the protection state of a virtual host by removing its deletion protection. While it doesn't directly delete anything, it changes a security configuration that makes a critical resource (virtual host) vulnerable to subsequent destructive actions.
From the tool's definition Remove deletion protection from a virtual host
Attacks that exploit this kind of access
Remove deletion protection from a virtual host. It is categorised as a Write tool in the Rabbitmq MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for unprotect-vhost: 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.
unprotect-vhost is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the unprotect-vhost 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 unprotect-vhost. 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.
unprotect-vhost 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 →