Retrieves messages from a Discord text channel with a configurable limit
AI agents call discord_read_messages to retrieve information from MCP-Discord without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing message data without creating, modifying, or deleting anything. It is a pure read operation with no side effects or capability to alter state. The configurable limit parameter only affects query scope, not data persistence. Severity is low because message retrieval in Discord is a normal, non-destructive operation with minimal risk of unintended harm even if an AI misuses it.
From the tool's definition Tool name contains 'read' and description states it 'Retrieves messages from a Discord text channel' with no mention of modification, deletion, or side effects.
Attacks that exploit this kind of access
Retrieves messages from a Discord text channel with a configurable limit. It is categorised as a Read tool in the MCP-Discord MCP Server, which means it retrieves data without modifying state.
Register the MCP-Discord MCP server in PolicyLayer and add a rule for discord_read_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 MCP-Discord. Nothing to install.
discord_read_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_read_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_read_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_read_messages is provided by the MCP-Discord MCP server (jackedelic/mcp-discord). 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 →