AI agents call discord_read_dms 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 DM message history without altering or deleting data. However, severity is elevated to 'medium' because DMs may contain sensitive personal information, authentication tokens, or confidential conversations; an AI agent with unconstrained access could exfiltrate private communications. The blast radius depends on what information users share in DMs with the bot.
From the tool's definition Tool name contains 'read' and description states 'Read the most recent messages from the bot' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Read the most recent messages from the bot. 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_read_dms: 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_read_dms 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_dms 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_dms. 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_dms is provided by the Discord MCP server (@pasympa/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 →