Sends a message to a specified Discord text channel. Optionally reply to another message by providing its message ID.
AI agents use discord_send to create or update resources in MCP-Discord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Discord environment.
The tool creates new content (a Discord message) but does not irreversibly destroy data, execute arbitrary code, or move money. While sending messages could have reputational or communication impacts if misused by an AI agent (e.g., spam, impersonation, or disclosure of sensitive information), the action itself is reversible and typical of Write-category operations.
From the tool's definition Tool description states it 'Sends a message to a specified Discord text channel', which creates new data (a message) in a reversible manner (messages can be edited or deleted by authorized users).
Documented attack patterns abuse exactly the kind of access discord_send gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Discord, and nothing reaches the server without passing your rules. This is the rule we recommend for discord_send:
{
"version": "1",
"default": "deny",
"tools": {
"discord_send": {
"limits": [
{
"counter": "discord_send_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}discord_send 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.
Free to start. No card required.
Sends a message to a specified Discord text channel. Optionally reply to another message by providing its message ID. It is categorised as a Write tool in the MCP-Discord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-Discord MCP server in PolicyLayer and add a rule for discord_send: 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 MCP-Discord. Nothing to install.
discord_send 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 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. 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 is provided by the MCP-Discord MCP server (barryyip0625/mcp-discord). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Discord, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
43 MCP-Discord tools catalogued and risk-classified — across an index of 43,000+ MCP servers.