AI agents use discord_send_message 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 creates new data (messages) in Discord channels or DMs without deleting or executing arbitrary code. It is reversible (messages can be deleted afterward). The severity is medium rather than high because while message sending could be abused for spam, harassment, or social engineering, the blast radius is limited to Discord communications and the messages themselves remain visible/auditable.
From the tool's definition Tool name 'discord_send_message' and description 'Send a message to a channel or user (DM)' indicate the tool creates/adds new messages, which is a reversible write operation.
Attacks that exploit this kind of access
Send a message to a channel or user (DM). Specify channelId OR userId. 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_send_message: 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_send_message 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_send_message 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_send_message. 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_send_message is provided by the Discord MCP server (tensakulabs/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 →