send_dm_embed

THE RISK

Medium Risk

Why send_dm_embed needs a policy

This tool writes data (creates a direct message) but does not delete, execute code, or move financial resources. The primary risk is that an AI agent could spam or send deceptive/harassing messages to users, affecting trust and compliance.

From the tool's definition Tool name 'send_dm_embed' and description 'Send a rich embed direct message to a server member' indicate the tool creates and sends a message, which is a write operation that modifies state (creates a new message resource) without being irreversible or…

Documented attack patterns abuse exactly the kind of access send_dm_embed gives an agent:

POLICY

How to control send_dm_embed

PolicyLayer is an MCP gateway — it sits between your AI agents and Discord, and nothing reaches the server without passing your rules. This is the rule we recommend for send_dm_embed:

policy.json

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

send_dm_embed 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.

Create a free account and register Discord — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Discord tools

Destructive bulk_delete_messages Delete multiple messages from a channel at once (2-100 messages). Only works on messages l Destructive delete_automod_rule Delete an auto-moderation rule from the Discord server. Destructive delete_channel Delete a channel from the Discord server. Channel name is fuzzy-matched. Destructive delete_command Delete an application (slash) command. Destructive delete_emoji Remove a custom emoji from the server by name or ID. Destructive delete_event Delete a scheduled event from the Discord server. Destructive delete_forum_tag Remove a tag from a forum channel. Destructive delete_integration Remove an integration from the server by its ID.

All 139 Discord tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about send_dm_embed

What does the send_dm_embed tool do? +

Send a rich embed direct message to a server member. The member is resolved by name, ID, or mention using fuzzy matching. 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 send_dm_embed? +

Register the Discord MCP server in PolicyLayer and add a rule for send_dm_embed: 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 send_dm_embed? +

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

Can I rate-limit send_dm_embed? +

Yes. Add a rate_limit block to the send_dm_embed 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 send_dm_embed completely? +

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

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

Enforce policy on every Discord tool call.

Start from Discord, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →