AI agents invoke cribl_restartWorkerGroup to trigger actions in Cribl. 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 an operational action (restart) on infrastructure components. While not destructive (data is not deleted), it triggers external effects that could interrupt data processing pipelines and cause service disruption. The impact depends on arguments (which worker group), classifying it as Execute rather than Read or Write.
From the tool's definition Tool name contains 'restart' and description states it 'Restarts all workers within the default or specified worker group.' Restarting worker groups triggers external operations (service restarts) whose effects depend on which worker group is targeted.
Attacks that exploit this kind of access
Restarts all workers within the default or specified worker group. It is categorised as a Execute tool in the Cribl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cribl MCP server in PolicyLayer and add a rule for cribl_restartWorkerGroup: 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 Cribl. Nothing to install.
cribl_restartWorkerGroup 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 cribl_restartWorkerGroup 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 cribl_restartWorkerGroup. 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.
cribl_restartWorkerGroup is provided by the Cribl MCP server (pebbletek/cribl-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 →