AI agents invoke resume-queue 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.
Resuming a queue is an operational/control action that changes the runtime state of the queue. It is not a simple read or write of data, nor is it destructive or financial. It triggers an external operation whose effects (messages begin flowing, consumers become active) depend on the current state of the system, placing it in the Execute category.
From the tool's definition "Resume a queue" — triggers an operational state change on a RabbitMQ queue (resuming a previously suspended/paused queue), which is an external operation with side effects on message delivery and consumer behavior.
Attacks that exploit this kind of access
Resume a queue. 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 resume-queue: 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.
resume-queue 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 resume-queue 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 resume-queue. 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.
resume-queue 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 →