Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Discord MCP

NPM · @ORYGN/DISCORD-MCP

Discord server management MCP for AI agents: chat, moderation, admin, and full server building.

Available components

+4 this week 84 Trust /100

Last scanned (21 hours ago)

Scores higher than 75% of npm servers

Category Communication

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 19 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to OrygnsCode/discord-mcp). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 22611 tokens (~137/item across 164 items; 164 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 77% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 29 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 165 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • Package version: 2.1.0 → 2.1.1 functional
  • 19 Nov 26 +1
    • Stability: 0.20 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 2.0.0 → 2.1.0 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1
    • Stability: unverified → 0.07 ▲ functional
  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 64

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@orygn/discord-mcp@2.1.1

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo OrygnsCode/discord-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/OrygnsCode/discord-mcp/.github/workflows/release.yml@refs/tags/v2.1.1
Rekor log index 4030686623
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:f6bcfbf400c3a89a174edd387335c704423f8036557bb85f35ea5d8a6e9f6bd9c736ac0e6d7d6d4f810c6cdf04e7d82d5073a841a620000dc7171a937

Background: How many MCP packages publish verified provenance →

Dependencies 19 packages
Packages resolved 19
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 164 exposed · ~22,249 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_reactions ~101

Add one or more reactions to a message in a single call. Takes unicode emoji directly or custom emoji by name.

NameTypeReqDescription
channelstringyesChannel name or ID.
emojisarrayyesEmoji to add, like a pasted emoji or a custom emoji name.
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesMessage ID, or the message's link.

No output schema declared.

No examples provided.

add_thread_member ~152

Pull a member into a thread. Adding someone to a private thread they cannot see now lets them read all of it, earlier messages included, so that needs confirming: the first call changes nothing and returns a preview and a confirm_token, and repeating the call with the token adds them.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
guildstring–Guild (server) name or ID. Omit to use the default guild.
memberstringyesMember name or user ID.
threadstringyesThread name or ID.

No output schema declared.

No examples provided.

assign_role ~229

Give a member a role. Preflights the bot's role hierarchy so the failure mode is an explanation, not a 403. Supports dry_run. A role that would give the member moderator or admin powers (such as banning, kicking, or timing out members, deleting other people's messages, or managing the server, roles, or channels), or let them see channels hidden from them now, needs confirming: the first call changes nothing and returns a preview and a confirm_token, and repeating the call with the token makes the change. Other roles are given at once.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean–Preview without assigning.
guildstring–Guild (server) name or ID. Omit to use the default guild.
memberstringyesMember name or user ID.
reasonstring–Audit log reason.
rolestringyesRole name or ID.

No output schema declared.

No examples provided.

audit_server_security ~122

Review a server's security the way an attacker would look at it, and list findings from high to low with a fix for each: powers held by everyone or by everyday roles, roles that can raise their own power through Manage Roles, bots with Administrator, powerful roles offered in onboarding or handed out by invites, 2FA for moderators, verification, the media filter, AutoMod, webhooks, and permanent invites. Read only; it changes nothing.

NameTypeReqDescription
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

ban_member ~197

Ban a user from the server, optionally deleting their recent messages. Works on users who already left (pass their user ID). Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token performs the ban. Relay the preview for the user's go-ahead.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
delete_message_secondsinteger–Also delete their messages from the last N seconds, up to 604800 (7 days).
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––
userstringyesMember name, or a user ID for someone not in the server.

No output schema declared.

No examples provided.

bulk_ban ~160

Ban up to 200 users at once by ID, for raid cleanup. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token performs the bans. Reports which bans succeeded and which failed.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
delete_message_secondsinteger––
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––
user_idsarrayyesUser IDs to ban.

No output schema declared.

No examples provided.

bulk_delete_messages ~227

Delete many recent messages at once (2 to 100), optionally filtered by author or text. Discord cannot bulk delete messages older than 14 days. Safe to call directly: the first call returns how many it would remove, with a sample of them, plus a confirm_token; repeating the call with the token deletes those same messages. Messages posted after the preview are left alone, so it works in a busy channel, such as during a raid.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
containsstring–Only delete messages containing this text.
countinteger–How many recent messages to scan. Default 50.
dry_runboolean––
from_authorstring–Only delete messages whose author name matches this.
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

bulk_update_roles ~160

Add or remove a role across every member matching a filter. Safe to call directly: the first call returns the affected count and a confirm_token; repeating the call with the token applies the change. Walks up to 3000 members and reports if it hits the cap.

NameTypeReqDescription
actionstringyes–
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
filterobject––
guildstring–Guild (server) name or ID. Omit to use the default guild.
rolestringyesRole name or ID.

No output schema declared.

No examples provided.

cancel_event ~132

Cancel and remove a scheduled event. Interested members lose the listing. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token cancels it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
eventstringyesEvent name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

cancel_scheduled_message ~133

Cancel a pending scheduled message by its id. The queued text is gone for good, and a repeat stops, so the first call returns a preview and a confirm_token; repeating the call with the token cancels it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
schedule_idstringyes–

No output schema declared.

No examples provided.

catch_up ~257

What happened in a server recently, in one call: every channel and thread with new messages since a time (default the last 24 hours), busiest first, with who talked, the messages themselves (trimmed), @everyone pings, and, with mentions_of, the messages that mention a member. Quiet channels are skipped without being read. Read only. For one channel's full history use read_messages.

NameTypeReqDescription
channelsarray–Only these channels (names or IDs); a category means the channels in it. Default: every channel the bot can read.
guildstring–Guild (server) name or ID. Omit to use the default guild.
hoursnumber–How far back to look, in hours. Default 24, at most 14 days.
max_channelsinteger–Most channels and threads read, taking the most recently active. Default 12.
mentions_ofstring–A member name or ID; messages that mention them are listed on their own.
per_channelinteger–Most messages read per channel. Default 30.
sincestring–Or an exact start time in ISO 8601, such as when the user was last here.

No output schema declared.

No examples provided.

clear_channel_permissions ~271

Remove a role's or member's permission overwrite from a channel, so their permissions there come from their roles and the other overwrites. On a category, Discord also makes the same change in every channel inside whose permissions match the category's exactly (synced), as the Discord app does; the result names them. To keep such a channel as it is, change that channel first, which stops it matching. get_channel_permissions says whether a channel is synced. Removing one that keeps someone out (a private channel's denial for @everyone, say) needs confirming, as does one whose removal gives moderator or admin powers (such as banning, kicking, or timing out members, deleting other people's messages, or managing the server, roles, or channels): the first call changes nothing and returns a preview and a confirm_token, and repeating the call with the token makes the change.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
guildstring–Guild (server) name or ID. Omit to use the default guild.
targetstringyesRole or member name or ID.

No output schema declared.

No examples provided.

clear_reactions ~173

Clear all reactions from a message, or all of one emoji. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token executes. Relay the preview for the user's go-ahead.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
emojistring–Only clear this emoji; omit to clear everything.
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesMessage ID, or the message's link.

No output schema declared.

No examples provided.

clone_channel ~81

Copy a channel's settings and permission overwrites into a new channel in the same category.

NameTypeReqDescription
channelstringyesChannel name or ID to copy.
guildstring–Guild (server) name or ID. Omit to use the default guild.
new_namestring–Name for the copy. Defaults to the original plus -copy.

No output schema declared.

No examples provided.

clone_role ~66

Copy a role's permissions, color, and settings into a new role.

NameTypeReqDescription
guildstring–Guild (server) name or ID. Omit to use the default guild.
new_namestring––
rolestringyesRole name or ID to copy.

No output schema declared.

No examples provided.

create_automod_rule ~338

Create a server-side moderation rule that runs on Discord's own infrastructure: Discord-maintained preset word lists (slurs, profanity, sexual content), custom keyword filters (with optional regex), spam detection, mention-flood limits, or member_profile checks on usernames, nicknames, and bios (Community servers only). For slur or hate-speech filtering prefer trigger keyword_preset with the slurs preset: Discord maintains the word list, so none needs to be written. Actions: block the message, alert a channel, and/or time the sender out (timeout is not available on spam, keyword_preset, or member_profile rules). On member_profile rules block quarantines the member until they fix their profile.

NameTypeReqDescription
actionsarrayyesWhat happens on a match.
alert_channelstring–Where alert actions post.
allow_listarray–Words exempt from keyword and keyword_preset rules.
enabledboolean–Default true.
exempt_channelsarray––
exempt_rolesarray––
guildstring–Guild (server) name or ID. Omit to use the default guild.
keywordsarray–For keyword rules. Wildcards: word* matches prefixes.
mention_limitinteger–For mention_spam rules: max unique mentions per message.
namestringyes–
presetsarray–For keyword_preset rules: Discord-maintained lists.
regex_patternsarray–For keyword rules; Rust-flavored regex.
timeout_minutesinteger–How long timeout actions last.
triggerstringyes–

No output schema declared.

No examples provided.

create_channel ~559

Create a text, voice, forum, stage, announcement, or category channel, optionally inside a category, and optionally private or read-only from the start. private_to, read_only and posting_roles compile to permission overwrites and are applied in the same call, so a private channel is one request rather than a create followed by set_channel_permissions. Use set_channel_permissions for anything finer. Voice and forum settings (bitrate, user limit, region, default reaction, sort, layout, required tags) can be set at creation too. Supports dry_run.

NameTypeReqDescription
bitrate_kbpsinteger–Voice and stage audio quality in kbps. Up to 96 without boosts, 128, 256, and 384 at boost levels 1 to 3.
categorystring–Category name or ID to place the channel under.
default_layoutstring–Forum: list or gallery view.
default_reactionstring–Forum: the emoji offered on every post, as a character or a custom emoji name; none to remove.
default_sortstring–Forum: how posts are ordered.
dry_runboolean–Preview without creating.
guildstring–Guild (server) name or ID. Omit to use the default guild.
namestringyesChannel name.
nsfwboolean––
post_slowmode_secondsinteger–Forum: the slowmode each new post starts with.
posting_rolesarray–Role names that may still post and start threads when read_only is set. Has no effect on its own.
private_toarray–Role names that can see the channel. Everyone else is denied View Channel, and Connect too on voice, stage and category. Do not list @everyone.
read_onlyboolean–Deny sending to everyone, for rules and announcement channels.
regionstring–Voice region id such as us-east or rotterdam, or automatic.
require_tagboolean–Forum: posts must carry at least one tag.
slowmode_secondsinteger–Per-user message cooldown.
thread_archive_minutesnumber–How long new threads stay open without activity: 60, 1440 (a day), 4320, or 10080 (a week).
topicstring–Channel topic, for text-like channels.
typestring–Channel type. Default text.
user_limitinteger–Most people at once, 0 for no limit. Up to 99 in voice, 10000 in stage.
video_qualitystring–Camera quality in voice channels: auto, or full (720p).

No output schema declared.

No examples provided.

create_emoji ~77

Upload a custom emoji from an image URL. Discord's limit for emoji files is 256 KB; png, jpeg, gif, and webp work.

NameTypeReqDescription
guildstring–Guild (server) name or ID. Omit to use the default guild.
image_urlstringyes–
namestringyes–

No output schema declared.

No examples provided.

create_event ~226

Create a Discord scheduled community event that members see on the events list and can mark interest in: a voice, stage, or external (in-person or off-platform) event. This is not for sending a message later (use schedule_message) or watching live activity (use subscribe_events). Voice and stage events need a channel; external events need a location and an end time.

NameTypeReqDescription
channelstring–Voice or stage channel, for those event types.
descriptionstring––
end_timestring–Required for external events.
guildstring–Guild (server) name or ID. Omit to use the default guild.
locationstring–Where an external event happens.
namestringyes–
repeatstring–Repeat the event. weekly and biweekly recur on the start's weekday; monthly recurs on the same weekday and week of the month.
start_timestringyesISO time, like 2026-07-01T19:00:00Z.
typestringyes–

No output schema declared.

No examples provided.

create_forum_post ~136

Start a post in a forum channel: a title, the opening message, optional tags from the forum's tag list, and up to 10 files fetched from public URLs.

NameTypeReqDescription
contentstringyes–
filesarray–Up to 10 files to attach, each fetched from a public URL (20 MiB each). Needs the Attach Files permission.
forumstringyesForum channel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
tagsarray–Tag names to apply.
titlestringyes–

No output schema declared.

No examples provided.

create_forum_tag ~81

Add a tag to a forum's tag list. Moderated tags can only be applied by people with Manage Threads.

NameTypeReqDescription
forumstringyesForum channel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
moderatedboolean––
namestringyes–

No output schema declared.

No examples provided.

create_invite ~332

Create an invite link for a channel. Defaults are deliberate: expires in 24 hours, unlimited uses. A never-expiring invite must be asked for explicitly with max_age_seconds 0. roles gives roles to whoever joins with it, and for_users limits it to particular people. An invite whose roles would give moderator or admin powers (such as banning, kicking, or timing out members, deleting other people's messages, or managing the server, roles, or channels), or open channels, needs confirming: the first call changes nothing and returns a preview and a confirm_token, and repeating the call with the token makes the change.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
for_usersarray–User IDs of the only people who can use it (up to 1000). They need not be in the server yet.
guildstring–Guild (server) name or ID. Omit to use the default guild.
max_age_secondsinteger–Lifetime in seconds, 0 for never. Default 86400 (24h).
max_usesinteger–Use limit, 0 for unlimited. Default 0.
rolesarray–Role names or IDs given to everyone who joins with this invite. Needs Manage Roles.
temporaryboolean–Members who join leave again when they disconnect.

No output schema declared.

No examples provided.

create_poll ~121

Post a native Discord poll: a question, two to ten answers, and a duration of up to 32 days.

NameTypeReqDescription
answersarrayyes–
channelstringyesChannel name or ID.
contentstring–Optional message text above the poll.
duration_hoursinteger–How long the poll runs. Default 24.
guildstring–Guild (server) name or ID. Omit to use the default guild.
multi_selectboolean–Allow choosing several answers.
questionstringyes–

No output schema declared.

No examples provided.

create_role ~329

Create a role from a vetted preset (none, member, moderator, admin) and/or an explicit list of permission names. Administrator is never granted by a preset; it must be spelled out explicitly. Can start with a gradient or holographic color and an icon where the server has those features. Supports dry_run.

NameTypeReqDescription
colorstring–Hex color like #00b0f4.
dry_runboolean–Preview without creating.
guildstring–Guild (server) name or ID. Omit to use the default guild.
hoistboolean–Show members separately in the sidebar.
holographicboolean–Discord's holographic style, which uses its own three colors; false for a solid color. Needs the Enhanced Role Colors server feature.
icon_emojistring–A standard emoji shown beside members' names instead of an image, or none to remove. Needs boost level 2.
icon_urlstring–Public URL of a small image (png, jpeg, webp; 256 KB) shown beside members' names, or none to remove. Needs boost level 2.
mentionableboolean––
namestringyesRole name.
permissionsarray–Extra permission names, like manage_messages or ban_members.
presetstring–Vetted permission bundle. Default none.
secondary_colorstring–A second hex color, so the role name shows a gradient from color to this one; none for a solid color. Needs the Enhanced Role Colors server feature.

No output schema declared.

No examples provided.

create_server_template ~65

Snapshot this server's structure as a Discord template others can create servers from. One template per server.

NameTypeReqDescription
descriptionstring––
guildstring–Guild (server) name or ID. Omit to use the default guild.
namestringyes–

No output schema declared.

No examples provided.

create_soundboard_sound ~113

Upload a soundboard sound from an audio URL: mp3 or ogg, up to 512 KB and 5.2 seconds. Servers start with eight sound slots; boosts add more.

NameTypeReqDescription
emojistring–An emoji to show with the sound.
guildstring–Guild (server) name or ID. Omit to use the default guild.
namestringyes–
sound_urlstringyes–
volumenumber–Playback volume. Default 1.

No output schema declared.

No examples provided.

create_sticker ~120

Upload a custom sticker from an image URL. Discord requires png, apng, or gif at 320x320 pixels and up to 512 KB. Servers start with five sticker slots; boosts add more.

NameTypeReqDescription
descriptionstring–Empty or 2-100 characters.
guildstring–Guild (server) name or ID. Omit to use the default guild.
image_urlstringyes–
namestringyes–
tagsstringyesComma separated keywords, or one emoji name for autocomplete.

No output schema declared.

No examples provided.

create_thread ~171

Start a thread in a text or announcement channel: standalone, branched from a message when message_id is given, or private (invite-only) when asked. For a post in a forum channel, use create_forum_post instead.

NameTypeReqDescription
auto_archive_minutesnumber–Inactivity timeout: 60, 1440, 4320, or 10080. Default 1440.
channelstringyesParent channel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstring–Branch the thread from this message (its ID or link).
namestringyes–
privateboolean–Invite-only thread; only works standalone.
slowmode_secondsinteger––

No output schema declared.

No examples provided.

create_webhook ~99

Create an incoming webhook on a channel. Webhooks post with any display name and avatar, which is how messages 'as someone' work legitimately.

NameTypeReqDescription
avatar_urlstring–Image for the webhook's default avatar, up to 1 MB.
channelstringyesChannel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
namestringyes–

No output schema declared.

No examples provided.

crosspost_message ~74

Publish a message in an announcement channel out to every server that follows it.

NameTypeReqDescription
channelstringyesAnnouncement channel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesMessage ID, or the message's link.

No output schema declared.

No examples provided.

delete_app_command ~173

Unregister a slash command so it no longer appears for users. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token removes it.

NameTypeReqDescription
botstring–Which bot to act as, by name, when more than one is configured. Omit to use the default bot, or with a server, the bot that handles it.
commandstringyesCommand name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

delete_automod_rule ~146

Delete an AutoMod rule; its protection stops immediately. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it. Turning it off with update_automod_rule is the reversible alternative.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
rulestringyesRule name or ID.

No output schema declared.

No examples provided.

delete_blueprint ~113

Delete a saved blueprint from the local store. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it. Servers built from it are untouched.

NameTypeReqDescription
blueprintstringyesBlueprint name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––

No output schema declared.

No examples provided.

delete_channel ~195

Delete a channel or category. Safe to call directly: the first call deletes nothing and returns a preview plus a confirm_token, and the deletion only happens when the call is repeated with that token. When the user asks to delete something, call this and relay the preview for their go-ahead instead of sending them to do it manually in Discord; the gate exists exactly so deletion can be approved through the conversation. Deleting a category leaves its channels in place, uncategorized.

NameTypeReqDescription
channelstringyesChannel or category name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––

No output schema declared.

No examples provided.

delete_emoji ~124

Delete a custom emoji. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
emojistringyesEmoji name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

delete_forum_post ~138

Delete a forum post and every reply in it. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
poststringyesPost title or thread ID.
reasonstring––

No output schema declared.

No examples provided.

delete_forum_tag ~146

Remove a tag from a forum; posts carrying it simply lose it. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token removes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
forumstringyesForum channel name or ID.
guildstring–Guild (server) name or ID. Omit to use the default guild.
tagstringyesTag name to remove.

No output schema declared.

No examples provided.

delete_integration ~136

Remove an integration from the server. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token removes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
integration_idstringyesIntegration ID from list_integrations.
reasonstring––

No output schema declared.

No examples provided.

delete_invite ~134

Revoke an invite link. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token revokes it.

NameTypeReqDescription
codestringyesThe invite code to revoke.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––

No output schema declared.

No examples provided.

delete_message ~183

Delete one message. Safe to call directly: the first call deletes nothing and returns a preview plus a confirm_token, and the deletion only happens when the call is repeated with that token. Use this two-step flow to let the user approve through the conversation rather than telling them to delete things by hand in Discord. Supports dry_run.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesThe message to delete: its ID or link.
reasonstring–Audit log reason.

No output schema declared.

No examples provided.

delete_role ~159

Delete a role. Members holding it simply lose it; nothing else changes. Safe to call directly: the first call deletes nothing and returns a preview plus a confirm_token, and the deletion only happens when the call is repeated with that token. Prefer this gated flow over telling the user to delete the role manually.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––
rolestringyesRole name or ID.

No output schema declared.

No examples provided.

delete_server_template ~134

Delete a server template; its share link stops working. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
codestringyesTemplate code, or its discord.new link.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

delete_soundboard_sound ~126

Delete a soundboard sound. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
soundstringyesSound name or ID.

No output schema declared.

No examples provided.

delete_sticker ~124

Delete a custom sticker. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
stickerstringyesSticker name or ID.

No output schema declared.

No examples provided.

delete_thread ~139

Delete a thread and its messages. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it. Archiving is the reversible alternative.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––
threadstringyesThread name or ID.

No output schema declared.

No examples provided.

delete_webhook ~139

Delete a webhook. Anything still posting through it stops working. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token deletes it.

NameTypeReqDescription
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
reasonstring––
webhookstringyesWebhook name or ID.

No output schema declared.

No examples provided.

diff_blueprint ~141

Compare a blueprint against the live server: what the blueprint expects but the server lacks (missing), what exists but differs (changed, with the fields), and what the server has that the blueprint never mentioned (extra, informational). Reads the blueprint as the whole truth, so a setting it leaves out counts as its default. The drift detector for config-as-code workflows. To act on it, plan_server_build applies changes with update_existing and deletes extras listed in remove.

NameTypeReqDescription
blueprint–yesA saved blueprint's name or ID, or a blueprint itself.
guildstring–Guild (server) name or ID. Omit to use the default guild.

No output schema declared.

No examples provided.

disconnect_member ~72

Remove a member from whatever voice channel they are in. They stay in the server; only the voice connection ends.

NameTypeReqDescription
guildstring–Guild (server) name or ID. Omit to use the default guild.
memberstringyesMember name or user ID.
reasonstring––

No output schema declared.

No examples provided.

edit_message ~226

Edit a message the bot itself sent, or one posted through one of the server's webhooks (that needs Manage Webhooks). Discord does not allow editing anyone else's messages, no matter the permission level. A message sent as a Components V2 layout stays one: edit it with components, never with content or embeds.

NameTypeReqDescription
channelstringyesChannel name or ID.
componentsarray–Rich layout, in place of content and embeds. Sending this sets the Components V2 flag, which is permanent for that message: it can never show plain content or embeds afterward, so the two cannot be c…
contentstring––
embedsarray–Up to 10 embeds. Each needs a title, a description, an author, fields, a footer, or a picture. Discord allows 6,000 characters of text across all of one message's embeds.
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesMessage ID, or the message's link.

No output schema declared.

No examples provided.

end_poll ~171

Close one of the bot's own polls early and finalize the results. Voting stops for good, since a poll cannot be reopened. Safe to call directly: the first call changes nothing and returns a preview plus a confirm_token; repeating the call with the token ends the poll. A poll that has already closed is left alone.

NameTypeReqDescription
channelstringyesChannel name or ID.
confirm_tokenstring–The token from this exact action's preview. Where the app can show a confirmation dialog, calling with it asks the user there, and it happens only if they agree.
dry_runboolean––
guildstring–Guild (server) name or ID. Omit to use the default guild.
message_idstringyesMessage ID, or the message's link.

No output schema declared.

No examples provided.

Install

How do I install the Discord MCP server?

Discord MCP runs locally as an npm package, launched with npx -y @orygn/discord-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @orygn/discord-mcp

# add to Claude Code
claude mcp add orygnscode-discord-mcp -- npx -y @orygn/discord-mcp
Common questions

What is the Discord MCP server?

Discord MCP is listed in the public MCP registry as io.github.OrygnsCode/discord-mcp. Discord server management MCP for AI agents: chat, moderation, admin, and full server building. This page covers its npm package (@orygn/discord-mcp).

Is the Discord MCP server safe to use?

Discord MCP scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Discord MCP server expose?

Discord MCP exposes 164 tools: get_rate_limit_status, get_bot_info, run_setup_check, get_server_overview, list_channels, and 159 more. Their descriptions and schemas cost roughly 22,249 tokens of context every time the server is loaded.

Is the Discord MCP server still maintained?

Discord MCP is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Discord MCP server under?

Discord MCP declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Discord MCP server?

VerifyMCP ran 16 checks on Discord MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.