This record as markdown: /tools/adamhancock-bullmq-mcp/drain-queue.md
What drain_queue does on BullMQ MCP Server
AI agents call drain_queue to permanently remove resources in BullMQ MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why drain_queue is rated Critical
This tool permanently removes all jobs from a queue without the ability to undo the operation. While not a financial transaction, the irreversible deletion of potentially critical job data (business-critical tasks, user requests, etc.) represents a destructive action with significant blast radius if triggered by an AI agent without proper intent. The data loss is immediate and complete for that queue.
From the tool's definition Tool named 'drain_queue' with description 'Remove all jobs from a queue' — irreversibly deletes all queued jobs in a single operation.
Attacks that exploit this kind of access
The rule that runs drain_queue safely
PolicyLayer is an MCP gateway: it sits between your AI agents and BullMQ MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For drain_queue, this is the rule to start with:
drain_queue is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect BullMQ MCP Server, apply this rule, and every drain_queue call is checked against it from then on.
Questions about drain_queue
Remove all jobs from a queue. It is categorised as a Destructive tool in the BullMQ MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BullMQ MCP Server MCP server in PolicyLayer and add a rule for drain_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 BullMQ MCP Server. Nothing to install.
drain_queue 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 drain_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 drain_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.
drain_queue is provided by the BullMQ MCP Server MCP server (adamhancock/bullmq-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on BullMQ MCP Server, and thousands of servers like it.
Across the catalogue