Discord Bot connector for AI agents

Tools your messaging agent reaches for on Discord Bot, scoped per tenant.

CALL ANY TOOL

Community ops from one API key: guilds, channels, members, roles, messages, threads, webhooks, and moderation rules. The token is vaulted, never in LLM context.

discordbot_list_active_guild_threads

List active guild threads

List all active threads in a guild, including public and private threads. returns a list of channel objects and thread member objects for the current user.

Parameters

Name

Type

Required

Description

guild_id

string

Required

The ID of the guild to list active threads from.

discordbot_get_answer_voters

Get answer voters

discordbot_search_guild_members

Search guild members

discordbot_create_application_emoji

Create application emoji

discordbot_bulk_update_lobby_members

Bulk update lobby members

discordbot_bulk_delete_messages

Bulk delete messages

discordbot_add_guild_member

Add guild member

discordbot_group_dm_remove_recipient

Group dm remove recipient

discordbot_list_application_emojis

List application emojis

discordbot_get_application_activity_instance

Get application activity instance

discordbot_search_guild_messages

Search guild messages

Search for messages matching a query across a discord guild. returns matching messages without the reactions key. requires the read_message_history permission and access is restricted according to whether the message_content privileged intent is enabled for the application. if the searched entity is not yet indexed, discord returns a 202 response instead of results.

Parameters

Name

Type

Required

Description

guild_id

string

Required

The ID of the guild to search messages in.

attachment_extension

array

Optional

Filter messages by attachment extension, e.g. txt (max 256 characters per entry, max 100 entries).

attachment_filename

array

Optional

Filter messages by attachment filename (max 1024 characters per entry, max 100 entries).

author_id

array

Optional

Filter messages by these author user IDs (max 100).

author_type

array

Optional

Filter messages by author type. Prefix a value with - to negate it, e.g. -bot.

channel_id

array

Optional

Filter messages by these channel IDs (max 500).

content

string

Optional

Filter messages by content (max 1024 characters).

embed_provider

array

Optional

Filter messages by embed provider name, case-sensitive, e.g. Tenor (max 256 characters per entry, max 100 entries).

embed_type

array

Optional

Filter messages by embed type (max 5 entries).

has

array

Optional

Filter messages by whether they have specific things. Prefix a value with - to negate it, e.g. -embed.

include_nsfw

boolean

Optional

Whether to include results from age-restricted channels. Defaults to false.

limit

integer

Optional

Max number of messages to return (1-25). Default is 25.

link_hostname

array

Optional

Filter messages by link hostname, e.g. discordapp.com (max 256 characters per entry, max 100 entries).

max_id

string

Optional

Get messages before this message ID.

mention_everyone

boolean

Optional

Filter messages by whether they do or do not mention @everyone.

mentions

array

Optional

Filter messages that mention these user IDs (max 100).

mentions_role_id

array

Optional

Filter messages that mention these role IDs (max 100).

min_id

string

Optional

Get messages after this message ID.

offset

integer

Optional

Number to offset the returned messages by (max 9975).

pinned

boolean

Optional

Filter messages by whether they are or are not pinned.

replied_to_message_id

array

Optional

Filter messages that reply to these message IDs (max 100).

replied_to_user_id

array

Optional

Filter messages that reply to these user IDs (max 100).

slop

integer

Optional

Max number of words to skip between matching tokens in the search content (max 100, default 2).

sort_by

string

Optional

The sorting algorithm to use: timestamp (default) or relevance. Sort order is not respected when sorting by relevance.

sort_order

string

Optional

The direction to sort: asc or desc. Defaults to desc.

discordbot_create_auto_moderation_rule

Create auto moderation rule

discordbot_update_application_role_connection_metadata

Update application role connection metadata

discordbot_delete_all_reactions

Delete all reactions

discordbot_add_guild_member_role

Add guild member role

discordbot_remove_guild_ban

Remove guild ban

discordbot_list_auto_moderation_rules

List auto moderation rules

discordbot_get_application_emoji

Get application emoji

discordbot_create_channel_invite

Create channel invite

discordbot_update_lobby_message_moderation_metadata

Update lobby message moderation metadata

discordbot_delete_all_reactions_for_emoji

Delete all reactions for emoji

discordbot_add_lobby_member

Add lobby member

discordbot_remove_guild_member_role

Remove guild member role

discordbot_list_channel_messages

List channel messages

discordbot_get_application_role_connection_metadata

Get application role connection metadata

discordbot_create_dm

Create dm

discordbot_delete_application_emoji

Delete application emoji

discordbot_add_thread_member

Add thread member

discordbot_remove_lobby_member

Remove lobby member

discordbot_list_default_soundboard_sounds

List default soundboard sounds

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the tenant, and your agent can read channels and post replies from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["discordbot"], toolNames: ["discordbot_list_channel_messages", "discordbot_list_guild_members", "discordbot_create_message"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["discordbot"], toolNames: ["discordbot_list_channel_messages", "discordbot_list_guild_members", "discordbot_create_message"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["discordbot"], toolNames: ["discordbot_list_channel_messages", "discordbot_list_guild_members", "discordbot_create_message"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/discordbot",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start running Discord community ops from your workflows.

Community triage

Copy the prompt

Copied

Summarize unanswered messages in [channel] from the last 24 hours.

Copy the prompt

Copied

List members who joined this week and have no assigned role.

Copy the prompt

Copied

Find messages in [channel] that mention an error code.

Moderation

Copy the prompt

Copied

Show the auto moderation rules on [guild] and what each one blocks.

Copy the prompt

Copied

Timeout [user_id] for 1 hour and log the reason.

Copy the prompt

Copied

List members with the moderator role on [guild].

Announcements

Copy the prompt

Copied

Post the release notes for v2.4 in [channel] and pin the message.

Copy the prompt

Copied

Create a thread on [message_id] titled Known issues.

Copy the prompt

Copied

Add the reaction eyes to the last message in [channel].

SEE HOW AUTH WORKS

Your users connect once. Their Discord Bot credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Discord Bot

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Discord Bot

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Discord Bot

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Discord Bot

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

ENGINEERING

Slack workflow agent (LangGraph)

LangGraph agent that drives multi-step Slack workflows: triggers, approvals, and follow-up actions per user identity.

Slack

View agent

OPS

Email-to-calendar scheduling agent

Read scheduling intent out of Gmail threads, resolve mutual free time, and create the Google Calendar event.

Gmail

Google Calendar

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Discord Bot today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Discord Bot as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Discord Bot API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Discord Bot?

Yes. Pass a tool name filter to listScopedTools so the messaging agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Discord Bot.

What happens when a user revokes Discord Bot access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Is a Discord bot token shared across all my tenants?

No. Each tenant registers its own bot token and Scalekit stores it in that tenant's namespace of the AES-256 vault. A call for one tenant can never resolve another tenant's token, and revoking one leaves the rest running.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit