Remove a user from a conversation.
AI agents call conversations_kick to permanently remove resources in Slack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Kicking a user from a conversation is a destructive action: the user loses access immediately and the action cannot be automatically reversed. In a workplace Slack environment, misuse could disrupt collaboration, remove legitimate members from critical channels, and cause organizational harm. It fits Destructive rather than Write because the membership removal is not trivially reversible through the same tool.
From the tool's definition 'Remove a user from a conversation' — removing a user is an irreversible administrative action that cannot be undone by the tool itself
Attacks that exploit this kind of access
Remove a user from a conversation. It is categorised as a Destructive tool in the Slack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Slack MCP server in PolicyLayer and add a rule for conversations_kick: 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 Slack. Nothing to install.
conversations_kick 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 conversations_kick 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 conversations_kick. 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.
conversations_kick is provided by the Slack MCP server (karbassi/slack-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 →