Restart a queue worker (e.g. to pick up new code after a deploy)
AI agents invoke restart_queue to trigger actions in Ploi MCP Server. 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 service restart command, which is an operational action that changes system state. While not destructive (data is not deleted), and not merely reading data, it actively runs an external operation (restarting a queue worker). The effects depend on what queue worker is targeted.
From the tool's definition The tool "restart_queue" performs a restart operation on a queue worker, which triggers an external action that modifies the running state of a service.
Attacks that exploit this kind of access
Restart a queue worker (e.g. to pick up new code after a deploy). It is categorised as a Execute tool in the Ploi MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ploi MCP Server MCP server in PolicyLayer and add a rule for restart_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 Ploi MCP Server. Nothing to install.
restart_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 restart_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 restart_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.
restart_queue is provided by the Ploi MCP Server MCP server (sudanese/ploi-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 →