discord-mcp

Discord audit log (admin)

discord_admin_audit_log

Read-only

Retrieve and filter recent Discord audit log entries to see who created, changed, or deleted channels, roles, permissions, members, messages, invites, and webhooks by user or action.

Instructions

Recent entries from Discord's own audit log: who created, changed or deleted channels, roles, permissions, members, messages, invites and webhooks. Filter by user or action. Actions: server_update, channel_create, channel_update, channel_delete, permission_create, permission_update, permission_delete, member_kick, member_ban, member_unban, member_update, member_roles_update, bot_add, role_create, role_update, role_delete, invite_create, invite_delete, webhook_create, webhook_delete, message_delete, message_bulk_delete, message_pin, message_unpin, thread_create, thread_update, thread_delete.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "discord_admin_audit_log"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`action`	No	One action name from the list
`before`	No	Only entries before this entry ID (paging)
`user_id`	No	Only actions by this user

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 12, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that: the log is Discord's own server-side audit trail and it covers creations, changes, and deletions across a defined set of entity types. It omits the required 'View Audit Log' permission and says nothing about entry ordering or how far back the log goes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose clause and coverage list come first, with the action vocabulary trailing as reference material. The long action enumeration is justified because the schema lacks an enum, though it reads as a run-on list appended to a sentence rather than a distinct reference block.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, zero-required-parameter tool with no output schema, the description covers filtering but not the shape of a returned entry or the default ordering and time coverage. An agent still has to guess whether results are newest-first and what fields an entry contains before presenting them to a user.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75%, and the description compensates for the notable gap: the `action` parameter has no enum in the schema, and the description supplies the full valid value list. It also maps user and action filtering onto the two filter parameters. The `limit` and `before` paging semantics are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Recent entries from Discord's own audit log,' then enumerates the entity types covered (channels, roles, permissions, members, messages, invites, webhooks). The 'Discord's own audit log' framing separates it cleanly from sibling tools like discord_admin_events or discord_admin_moderate_member, which observe different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Filter by user or action' implies how to narrow results but gives no explicit when-to-use versus when-not-to-use, and no prerequisites. There is no alternative audit/history tool among the siblings, so the routing risk is low, but the guidance is only implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server