Deletes a Discord category by ID.
AI agents call discord_delete_category to permanently remove resources in MCP-Discord — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible destructive action—deletion of a category, which typically contains multiple channels and cannot be undone. The blast radius is significant as it affects server organization and potentially removes access to all channels within that category. This is the most severe applicable category per the hierarchy.
From the tool's definition Tool name 'discord_delete_category' and description 'Deletes a Discord category by ID' explicitly indicate irreversible deletion of a Discord organizational structure.
Attacks that exploit this kind of access
Deletes a Discord category by ID. It is categorised as a Destructive tool in the MCP-Discord MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP-Discord MCP server in PolicyLayer and add a rule for discord_delete_category: 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 MCP-Discord. Nothing to install.
discord_delete_category 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 discord_delete_category 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_delete_category. 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_delete_category is provided by the MCP-Discord MCP server (jackedelic/mcp-discord). 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 →