AI agents call list-vhosts to retrieve information from Rabbitmq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that lists virtual hosts. It retrieves data from the RabbitMQ cluster without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an attacker could only gain visibility into the cluster's virtual host configuration, not cause data loss or unauthorized actions.
From the tool's definition Tool name 'list-vhosts' and description 'List all virtual hosts in the cluster' indicate a query operation that retrieves information without modification or side effects.
Attacks that exploit this kind of access
List all virtual hosts in the cluster. It is categorised as a Read tool in the Rabbitmq MCP Server, which means it retrieves data without modifying state.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for list-vhosts: 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.
list-vhosts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list-vhosts 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 list-vhosts. 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.
list-vhosts 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 →