AI agents invoke clo_shutdown to trigger actions in Clo3d. 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 terminates an active listener process within CLO3D, which is an external operation that affects the running state of the application. It doesn't delete data, but it disrupts the MCP session and transfers control back to the UI, potentially interrupting ongoing workflows. It's an Execute-category action because it triggers an external operational state change.
From the tool's definition Stop the in-CLO listener and hand control back to CLO's UI
Attacks that exploit this kind of access
Stop the in-CLO listener and hand control back to CLO's UI. It is categorised as a Execute tool in the Clo3d MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Clo3d MCP server in PolicyLayer and add a rule for clo_shutdown: 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 Clo3d. Nothing to install.
clo_shutdown 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 clo_shutdown 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 clo_shutdown. 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.
clo_shutdown is provided by the Clo3d MCP server (lilbonner/clo3d-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 →