Ban a member from the server
AI agents call ban_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.
Banning a member is a severe, difficult-to-reverse moderation action. While an unban is technically possible, the act itself is destructive in nature — it forcibly removes a user from the server and deletes their membership. Misuse by an AI agent could result in mass banning of members, causing significant and hard-to-recover community damage.
From the tool's definition 'Ban a member from the server' — banning is an irreversible removal action (without manual unban) that expels a user and deletes their ability to rejoin
Attacks that exploit this kind of access
Ban 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 ban_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.
ban_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 ban_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 ban_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.
ban_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 →