AI agents use discord_edit_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.
Editing message content is a Write operation: it modifies data reversibly without deletion or irreversible destruction. Severity is medium because editing DMs could be used to alter communications in ways that mislead users or violate conversation integrity, but the scope is limited to the bot's own messages and the action is not destructive.
From the tool's definition Tool name and description specify 'Edit the text content of a DM message'—a modification operation. The action is reversible and limited to the bot's own messages ('Only the bot').
Attacks that exploit this kind of access
Edit the text content of a DM message previously sent by this bot. Only 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_edit_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_edit_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_edit_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_edit_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_edit_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 →