AI agents use add_reaction 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.
Adding a reaction is a reversible modification operation that creates new data (the reaction association) without deleting, executing code, or causing financial impact. It fits the Write category as a creation/modification action. Severity is low because the blast radius of accidental misuse is minimal—reactions are cosmetic, easily removable, and non-destructive to core server data or functionality.
From the tool's definition Tool name 'add_reaction' and description 'Add a reaction to a message' indicate creating/modifying message metadata by appending a reaction emoji.
Attacks that exploit this kind of access
Add a reaction to a message. 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 add_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.
add_reaction 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 add_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 add_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.
add_reaction 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 →