AI agents use discord_reply_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.
This tool sends a new message as a reply in a DM conversation. It creates new content (reversible in nature) without deleting or modifying existing data. Since it sends messages to direct message conversations on behalf of the bot, misuse could enable harassment or spam in private channels, warranting a medium severity rating.
From the tool's definition Reply to a specific message in a DM, attaching a quoted reply reference
Attacks that exploit this kind of access
Reply to a specific message in a DM, attaching a quoted reply reference. Unlike the edit/delete DM tools, this works on any message in the conversation (the bot. 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 discord_reply_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.
discord_reply_dm 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 discord_reply_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.
Set action: deny in the PolicyLayer policy for discord_reply_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.
discord_reply_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.
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 →