Discord Notifications MCP Server
Enables AI agents to interact with Discord by sending notifications, creating channels, and managing interactive questions with support for two-way responses. It allows for streamlined communication through channel keys and supports various question types like multiple-choice and extended-answer modals.
README
Discord Notifications MCP Server
MCP server that gives AI coding agents access to Discord: send notifications to multiple channels, create channels for new projects, and post questions (yes/no, multiple choice, extended answer) with optional two-way response.
Requirements
- Python 3.10+
- A Discord Bot: create an application, add a bot, copy the token. Invite the bot to your server with scopes:
bot, permissions: Send Messages, View Channels, Manage Channels, Read Message History, Use Slash Commands (if needed). For questions with buttons, enable Message Content Intent in the Bot settings.
Config
| Env / file | Purpose |
|---|---|
DISCORD_BOT_TOKEN or DISCORD_TOKEN |
Bot token (required). |
DISCORD_GUILD_ID |
Default guild ID for list_channels when guild_id is omitted. |
DISCORD_CHANNELS |
JSON map of channel keys → IDs, e.g. {"general": "123","alerts": "456"}. |
DISCORD_MCP_CONFIG_DIR |
Directory for channels.json (default: current dir). |
channels.json |
Same as DISCORD_CHANNELS: {"general": 123, "alerts": 456}. |
Channel keys let agents use send_notification("general", "Done.") instead of raw channel IDs.
Install and run
cd mcp-discord-notify
pip install -r requirements.txt
export DISCORD_BOT_TOKEN=your_bot_token
# optional: export DISCORD_GUILD_ID=your_server_id
# optional: create channels.json or set DISCORD_CHANNELS
python main.py
The server runs over stdio (JSON-RPC). Configure your MCP client to run:
- Command:
python(oruv run python) - Args:
["/absolute/path/to/mcp-discord-notify/main.py"] - Env:
DISCORD_BOT_TOKEN=...(and optionallyDISCORD_GUILD_ID,DISCORD_CHANNELS)
Cursor
Add to MCP settings (or .cursor/mcp.json):
{
"mcpServers": {
"discord-notifications": {
"command": "python",
"args": ["/home/skitz0/Documents/claude-cord/mcp-discord-notify/main.py"],
"env": {
"DISCORD_BOT_TOKEN": "your_bot_token",
"DISCORD_GUILD_ID": "your_guild_id"
}
}
}
}
Use the real path to main.py and set the env vars (or rely on your shell env).
Tools
| Tool | Description |
|---|---|
| list_channels | List channels in a guild (id, name, key if in config). |
| send_notification | Send a message to a channel (by ID or key). |
| create_channel | Create a text channel; optional register_key to save for future use by name. |
| send_question | Post a question with yes/no, multiple choice, or extended answer; optionally wait for first response. |
Questions (two-way)
- yes_no: Two buttons (Yes / No).
- multiple_choice: Buttons per option; pass
optionsas JSON array string, e.g.["A","B","C"]. - extended: "Reply" button opens a modal for long-form text.
Set wait_timeout_seconds (default 300); the tool returns the first response or timeout.
New project channels
Use create_channel with register_key so agents can target the channel by name. See the project skill: .cursor/skills/discord-notifications/SKILL.md.
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.