AI agents use create_category 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 creates a new Discord channel category, which is a write operation that organizes channels but does not delete, execute arbitrary code, or move money. The action is reversible (the category can be deleted). Severity is medium because an AI agent could spam categories or disrupt server organization, but the blast radius is limited to structural metadata rather than message content or user access control.
From the tool's definition Tool creates a new channel category in a Discord server. The description states 'Create a new channel category' — a reversible data creation operation.
Attacks that exploit this kind of access
Create a new channel category in a Discord server. Categories are used to group text and voice channels. 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 create_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 Discord. Nothing to install.
create_category 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 create_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 create_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.
create_category is provided by the Discord MCP server (ngoctranfire/discord-mcp-server). 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 →