AI agents invoke start-vhost-on-node to trigger actions in Rabbitmq. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a command that starts or restarts a virtual host on a specific node. While not destructive (the vhost itself is not deleted), and not a read operation, it performs a server operation whose effects depend on which vhost and node are specified. Restarting a vhost can disrupt message processing and client connections, making it an Execute-category risk.
From the tool's definition Tool name 'start-vhost-on-node' and description 'Start or restart a virtual host on a node' indicate execution of operational commands that trigger state changes in RabbitMQ infrastructure.
Attacks that exploit this kind of access
Start or restart a virtual host on a node. It is categorised as a Execute tool in the Rabbitmq MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rabbitmq MCP server in PolicyLayer and add a rule for start-vhost-on-node: 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.
start-vhost-on-node is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start-vhost-on-node 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 start-vhost-on-node. 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.
start-vhost-on-node 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 →