AI agents call discord_get_unread 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 queries Discord to retrieve unread message metadata. It has no side effects—it only reads state. The description is incomplete ("Get messages you haven"), but the name and context among sibling read tools confirm its read-only nature. Severity is low because misuse (e.g., an agent reading all unread messages) poses minimal direct harm, though the broader server's use of a selfbot violates Discord ToS.
From the tool's definition Tool name and description indicate it retrieves unread messages ("Get messages you haven") without modifying, deleting, or executing actions.
Attacks that exploit this kind of access
Get messages you haven. 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_unread: 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_unread 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_unread 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_unread. 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_unread 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 →