discord_send_dm · Discord MCP: Risk & Policy

WHAT IT DOES

What discord_send_dm does on Discord

AI agents use discord_send_dm 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.

WHY IT NEEDS A POLICY

Why discord_send_dm needs a policy

This tool creates new data (a direct message) in an irreversible manner—once sent, the message exists in the user's DM history. However, the message itself can be deleted, so it does not meet the Destructive threshold (which requires truly irreversible actions like data purging). It is Write rather than Read because it modifies system state by creating a message.

From the tool's definition Tool description states it 'Send[s] a private direct message to a user' which creates a new message artifact in Discord's systems. The description explicitly mentions it 'Returns the new message ID', confirming a persistent creation action.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

discord_send_dm Rate-limited

discord_send_dm stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "discord_send_dm": {
      "limits": [
        {
          "counter": "discord_send_dm_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Discord, so you can run agents against it safely.

FAQ

Questions about discord_send_dm

What does the discord_send_dm tool do? +

Send a private direct message to a user by their user ID. Use discord_send_message to post in a server channel instead. Requires the bot to share at least one server with the user, and the user must allow DMs from server members (otherwise Discord rejects the send). Returns the new message ID. 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.

How do I enforce a policy on discord_send_dm? +

Register the Discord MCP server in PolicyLayer and add a rule for discord_send_dm: 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.

What risk level is discord_send_dm? +

discord_send_dm is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit discord_send_dm? +

Yes. Add a rate_limit block to the discord_send_dm 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.

How do I block discord_send_dm completely? +

Set action: deny in the PolicyLayer policy for discord_send_dm. 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.

What MCP server provides discord_send_dm? +

discord_send_dm 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.