Remove a guest from a task
AI agents call remove-guest-from-task to permanently remove resources in ClickUp Operator — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a guest from a task revokes their access. While not deleting data, it is an access revocation action that is not trivially reversible (the guest must be explicitly re-added), making it closer to Destructive than Write. The blast radius is medium since it affects collaboration access for potentially important tasks.
From the tool's definition 'Remove a guest from a task' — removing access/membership is typically irreversible without re-inviting
Attacks that exploit this kind of access
Remove a guest from a task. It is categorised as a Destructive tool in the ClickUp Operator MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ClickUp Operator MCP server in PolicyLayer and add a rule for remove-guest-from-task: 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 ClickUp Operator. Nothing to install.
remove-guest-from-task 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 remove-guest-from-task 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 remove-guest-from-task. 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.
remove-guest-from-task is provided by the ClickUp Operator MCP server (noah-vh/mcp-server-clickup). 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 →