Remove the bot
AI agents call remove_reaction 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.
Removing a reaction deletes existing data (an emoji reaction) from a Discord message. While low blast radius (reactions are minor data), the action is a deletion/removal that cannot be undone, placing it in the Destructive category. Confidence is moderate because the description is truncated and uninformative.
From the tool's definition 'remove_reaction' and 'Remove the bot' — the description is incomplete/truncated, but the tool name strongly implies removing a reaction (an emoji response) from a message, which is an irreversible removal action.
Attacks that exploit this kind of access
Remove the bot. 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 remove_reaction: 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.
remove_reaction 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 remove_reaction 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 remove_reaction. 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.
remove_reaction 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 →