AI agents call list_channel_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.
This tool retrieves historical message data from a Discord channel without creating, modifying, or deleting any content. It has no side effects and poses minimal risk if an AI agent misuses it—the worst outcome would be unauthorized information disclosure from channels the bot token has access to. Low severity reflects the limited blast radius of read operations.
From the tool's definition Tool description states 'List recent messages in a channel' — a retrieval operation with no modification or side effects. The verb 'list' and the context of reading message history confirm read-only behavior.
Attacks that exploit this kind of access
List recent messages in a channel (newest first in the response). 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 list_channel_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.
list_channel_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 list_channel_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 list_channel_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.
list_channel_messages is provided by the Discord MCP server (taka392/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 →