discord_dm_user

Send a DM to a user (human-in-the-loop by default).

SERVERDiscord MCP Server SOURCEbennettschwartz/discord-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/bennettschwartz-discord-mcp/discord-dm-user.md

WHAT IT DOES

What discord_dm_user does on Discord MCP Server

AI agents use discord_dm_user to create or update resources in Discord MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Discord MCP Server environment.

RISK

Why discord_dm_user is rated Medium

This tool creates/writes data (a new direct message) but does not delete, execute arbitrary operations, or move money. The human-in-the-loop safeguard reduces severity from high to medium, but misuse could enable spam, phishing, or harassment at scale if an agent sends numerous DMs without proper authorization.

From the tool's definition Tool name is 'discord_dm_user' and description states 'Send a DM to a user'. Sending a direct message creates new data (message records) in Discord's system and modifies user conversation state reversibly.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs discord_dm_user safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Discord MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For discord_dm_user, this is the rule to start with:

discord_dm_user Rate-limited

discord_dm_user 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_dm_user": {
      "limits": [
        {
          "counter": "discord_dm_user_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Discord MCP Server, apply this rule, and every discord_dm_user call is checked against it from then on.

FAQ

Questions about discord_dm_user

What does the discord_dm_user tool do? +

Send a DM to a user (human-in-the-loop by default). It is categorised as a Write tool in the Discord MCP Server 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_dm_user? +

Register the Discord MCP Server MCP server in PolicyLayer and add a rule for discord_dm_user: 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 MCP Server. Nothing to install.

What risk level is discord_dm_user? +

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

Can I rate-limit discord_dm_user? +

Yes. Add a rate_limit block to the discord_dm_user 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_dm_user completely? +

Set action: deny in the PolicyLayer policy for discord_dm_user. 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_dm_user? +

discord_dm_user is provided by the Discord MCP Server MCP server (bennettschwartz/discord-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Discord MCP Server, and thousands of servers like it.

This server

All 58 Discord MCP Server tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →