Generate a server-wide permission report: for every channel that has overwrites, lists each role/member and their allowed/denied permissions (entity names resolved). Read-only. Returns { channels: [...] } with channel, channelId, overwrites. Use discord_get_channel_permissions for a single channel.
AI agents call discord_audit_permissions 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 only reads and reports existing permission data across channels. It has no side effects, creates no changes, and performs no operations that would modify, delete, or execute anything. The explicit 'Read-only' designation confirms it belongs in the Read category.
From the tool's definition Tool description explicitly states 'Read-only' and 'Generate a server-wide permission report' that 'lists each role/member and their allowed/denied permissions'. The tool retrieves and queries permission data without modification.
Attacks that exploit this kind of access
Generate a server-wide permission report: for every channel that has overwrites, lists each role/member and their allowed/denied permissions (entity names resolved). Read-only. Returns { channels: [...] } with channel, channelId, overwrites. Use discord_get_channel_permissions for a single channel. 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_audit_permissions: 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_audit_permissions 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_audit_permissions 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_audit_permissions. 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_audit_permissions 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 →