mcp-client-discord
Listens for Discord @mentions via Gateway and queues them for processing by an agent, exposing a tool to retrieve pending mentions for automated responses.
README
mcp-client-discord
Discord Event Listener with Claude-Powered Auto-Response via KADI Broker.
Overview
mcp-client-discord is a TypeScript-based MCP server that listens for Discord @mentions and queues them for template-agent-typescript to process. It uses Discord Gateway to receive real-time events.
Architecture
Discord Channel → Gateway Event → Mention Queue → template-agent-typescript → Claude API → mcp-server-discord → Discord Reply
Components
- Discord Gateway: Real-time WebSocket connection for receiving events
- Mention Queue: In-memory queue (max 100) of unprocessed @mentions
- MCP Server: Exposes
get_discord_mentionstool for KADI broker integration - Tool Registration: Available to any KADI agent via broker
Setup
1. Install Dependencies
npm install
2. Configure Environment
Copy .env.example to .env:
cp .env.example .env
Edit .env with your Discord bot token:
DISCORD_TOKEN=your_discord_bot_token_here
DISCORD_GUILD_ID=your_discord_guild_id_here # Optional
MCP_LOG_LEVEL=info
3. Get Discord Bot Token
- Go to Discord Developer Portal
- Create a new application
- Go to "Bot" section
- Click "Reset Token" and copy the token
- Enable "Message Content Intent" in bot settings
- Invite bot to your server with proper permissions (Send Messages, Read Messages, etc.)
4. Build
npm run build
5. Run
Development mode (with hot-reload):
npm run dev
Production mode:
npm start
MCP Tools
get_discord_mentions
Retrieve pending Discord @mentions from the queue.
Input:
limit(optional): Maximum number of mentions to retrieve (1-50, default: 10)
Output:
{
"mentions": [
{
"id": "message_id",
"user": "user_id",
"username": "username",
"text": "message text without @bot mention",
"channel": "channel_id",
"channelName": "channel_name",
"guild": "guild_id",
"ts": "ISO_timestamp"
}
],
"count": 1,
"retrieved_at": "ISO_timestamp"
}
Integration with KADI Broker
The MCP server is registered in kadi-broker/config/mcp-upstreams.json:
{
"id": "discord-client",
"name": "Discord Event Listener (mcp-client-discord)",
"type": "stdio",
"prefix": "discord_client",
"enabled": true,
"stdio": {
"command": "node",
"args": ["C:\\p4\\Personal\\SD\\mcp-client-discord\\dist\\index.js"],
"env": {
"DISCORD_TOKEN": "your_token",
"DISCORD_GUILD_ID": "your_guild_id"
}
},
"networks": ["discord"]
}
Event Topics
Topic Pattern Standard
All KĀDI events follow the standardized topic pattern: {platform}.{event_type}.{bot_id}
{platform}: Platform identifier (slack,discord, etc.){event_type}: Event type (app_mention,mention, etc.){bot_id}: Bot unique identifier (critical for multi-bot deployments)
Why bot_id is required:
- ✅ Enables multiple bot instances in the same server
- ✅ Routes events only to the intended bot
- ✅ Prevents cross-bot event delivery
- ✅ Supports multi-tenant deployments
Validation: Topics are automatically validated by @agents/shared package. Invalid patterns will log warnings but still publish.
See TOPIC_PATTERN.md for complete documentation.
discord.mention.{BOT_USER_ID}
Published when the bot is @mentioned in Discord.
Event Payload (DiscordMentionEvent):
{
id: string; // Unique message ID
user: string; // Discord user ID who mentioned the bot
username: string; // Discord username
text: string; // Message text (with @bot mention removed)
channel: string; // Discord channel ID
channelName: string; // Discord channel name
guild: string; // Discord guild/server ID
ts: string; // ISO 8601 timestamp
timestamp: string; // ISO 8601 datetime when event was published
}
Usage with Agent_TypeScript
Agent_TypeScript polls this MCP server for new @mentions:
// In Agent_TypeScript
const protocol = client.getBrokerProtocol();
const result = await protocol.invokeTool({
targetAgent: 'discord-client',
toolName: 'discord_client_get_discord_mentions',
toolInput: { limit: 5 },
timeout: 10000
});
const mentions = JSON.parse(result.content[0].text).mentions;
Discord Bot Permissions
Required bot permissions:
- View Channels
- Send Messages
- Read Message History
- Add Reactions (optional)
Required Gateway Intents:
- Guilds
- Guild Messages
- Message Content
Logging
The server logs to console with emoji indicators:
- 🚀 Startup messages
- 📬 Mention queued
- 📤 Mentions retrieved
- ✅ Success messages
- ❌ Error messages
- 💬 Received mention
Troubleshooting
"Discord client not ready after timeout"
- Check DISCORD_TOKEN is valid
- Verify bot has been invited to server
- Ensure internet connection is stable
"Channel not found" errors
- Verify bot has access to the channel
- Check channel permissions
Bot not responding to mentions
- Verify "Message Content Intent" is enabled
- Check bot has "Send Messages" permission
- Ensure bot is not muted or blocked
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.