discord_send · MCP-Discord MCP: Risk & Policy

WHAT IT DOES

What discord_send does on MCP-Discord

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.

WHY IT NEEDS A POLICY

Why discord_send needs a policy

Sending messages creates new data in Discord channels. This is a Write operation because messages can be edited or deleted afterward, making it reversible and not destructive. Severity is medium because an AI agent sending messages could spam channels, impersonate users, post malicious content, or disrupt communications, but the impact is limited to that channel and messages remain recoverable.

From the tool's definition Tool name 'discord_send' and description 'Sends a message to a specified Discord text channel' indicate creation of new message content, which is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

discord_send Rate-limited

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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP-Discord, so you can run agents against it safely.

FAQ

Questions about discord_send

What does the discord_send tool do? +

Sends a message to a specified Discord text channel. 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.

How do I enforce a policy on discord_send? +

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.

What risk level is discord_send? +

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

Can I rate-limit discord_send? +

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.

How do I block discord_send completely? +

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.

What MCP server provides discord_send? +

discord_send is provided by the MCP-Discord MCP server (jar285/mcp-discord). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.