AI agents call discord_get_messages to retrieve information from Discord without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves message data from Discord channels without creating, modifying, deleting, or executing anything. While the severity is elevated to medium (not low) due to the fact that it operates via a selfbot using a user token that violates Discord ToS and could access private/sensitive messages from multiple servers and DMs, the core action remains read-only.
From the tool's definition Tool description states 'Get messages from a channel', which is a retrieval operation with no side effects. The verb 'Get' and the lack of any modification or deletion semantics clearly indicate a read-only operation.
Attacks that exploit this kind of access
Get messages from a channel. Uses local cache if daemon is running, Discord API otherwise. It is categorised as a Read tool in the Discord MCP Server, which means it retrieves data without modifying state.
Register the Discord MCP server in PolicyLayer and add a rule for discord_get_messages: 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_get_messages is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the discord_get_messages 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_get_messages. 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_get_messages 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 →