AI agents use discord_unban_member to create or update resources in Discord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Discord environment.
This tool modifies server state by removing a ban restriction on a member, allowing them to rejoin. It is reversible (the user can be re-banned if needed), making it Write rather than Destructive. While it affects access controls, the impact is limited to a single user's membership status and is fully auditable.
From the tool's definition Lift a ban so the user may rejoin via a new invite. Requires the Ban Members permission. Reverses discord_ban_member. The reason is recorded in the audit log.
Attacks that exploit this kind of access
Lift a ban so the user may rejoin via a new invite. Requires the Ban Members permission. Reverses discord_ban_member. The reason is recorded in the audit log. It is categorised as a Write tool in the Discord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Discord MCP server in PolicyLayer and add a rule for discord_unban_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.
discord_unban_member is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the discord_unban_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 discord_unban_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.
discord_unban_member is provided by the Discord MCP server (@pasympa/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 →