// SCAN REPORT

Discord

68 tools. 45 can modify or destroy data without limits.

13 destructive tools with no built-in limits. Policy required.

Last updated: 5 Apr 2026

45 can modify or destroy data

23 read-only

68 tools total

Free to start. No card required.

TOOL MAP

Read (23) Write / Execute (32) Destructive / Financial (13)

WHAT CAN GO WRONG

Destructive tools (discord_ban_member, discord_delete_automod_rule, discord_delete_channel) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (discord_add_reaction, discord_add_role, discord_create_automod_rule) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

RECOMMENDED RULES

Deny destructive operations

{
  "discord_ban_member": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "discord_add_reaction": {
    "limits": [
      {
        "counter": "discord_add_reaction_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "discord_get_audit_log": {
    "limits": [
      {
        "counter": "discord_get_audit_log_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

ALL 68 DISCORD TOOLS

DESTRUCTIVE 13 tools

Destructive discord_ban_member Destructive discord_delete_automod_rule Destructive discord_delete_channel Destructive discord_delete_emoji Destructive discord_delete_event Destructive discord_delete_invite Destructive discord_delete_message Destructive discord_delete_role Destructive discord_delete_sticker Destructive discord_delete_webhook Destructive discord_kick_member Destructive discord_leave_guild Destructive discord_prune_members

WRITE 32 tools

Write discord_add_reaction Write discord_add_role Write discord_create_automod_rule Write discord_create_channel Write discord_create_emoji Write discord_create_event Write discord_create_invite Write discord_create_role Write discord_create_webhook Write discord_edit_automod_rule Write discord_edit_channel Write discord_edit_guild Write discord_edit_message Write discord_edit_onboarding Write discord_edit_role Write discord_edit_webhook Write discord_edit_welcome_screen Write discord_move_member Write discord_pin_message Write discord_remove_channel_permissions Write discord_remove_reaction Write discord_remove_role Write discord_send_message Write discord_set_channel_permissions Write discord_set_nickname Write discord_set_role_positions Write discord_setup_community Write discord_setup_onboarding Write discord_sync_channel_permissions Write discord_timeout_member Write discord_unban_member Write discord_unpin_message

FAQ

Can an AI agent delete data through the Discord MCP server? +

Yes. The Discord server exposes 13 destructive tools including discord_ban_member, discord_delete_automod_rule, discord_delete_channel. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Discord? +

The Discord server has 32 write tools including discord_add_reaction, discord_add_role, discord_create_automod_rule. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Discord.

How many tools does the Discord MCP server expose? +

68 tools across 3 categories: Destructive, Read, Write. 23 are read-only. 45 can modify, create, or delete data.

How do I enforce a policy on Discord? +

Register the Discord MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies for each. Same risk classification, live on your fleet in minutes.

Enforce policy on every Discord tool call.

Deterministic rules across all 68 Discord tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

SECURE DISCORD →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

Discord

// TOOL MAP

// WHAT CAN GO WRONG

// RECOMMENDED RULES

// ALL 68 DISCORD TOOLS

// FAQ