Kick a member from the server
AI agents call kick_member to permanently remove resources in Discord — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Kicking a member removes them from the server. While theoretically the user could rejoin via invite, from the server's perspective the action is not automatically reversible and has a high blast radius if misused by an AI agent — it could remove legitimate members en masse. This falls under Destructive as it irreversibly removes access without an undo mechanism.
From the tool's definition "Kick a member from the server" — removing a member is a significant moderation action that is not easily reversible (the user must be re-invited or rejoin).
Attacks that exploit this kind of access
Kick a member from the server. It is categorised as a Destructive tool in the Discord MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Discord MCP server in PolicyLayer and add a rule for kick_member: 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 Discord. Nothing to install.
kick_member 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 kick_member 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 kick_member. 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.
kick_member is provided by the Discord MCP server (scarecr0w12/discord-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 →