Discord MCP
Enables AI assistants to interact with Discord servers, including listing servers/channels, sending messages, and managing reaction-based opt-in campaigns.
README
Discord MCP Server
ā ļø ALPHA SOFTWARE - This project is in early alpha development. Features may be incomplete or buggy. Use at your own risk.
A Model Context Protocol (MCP) server that provides Discord integration tools for AI assistants like Claude.
Current Version: 0.0.1-alpha1 (Local Development)
Project Status
- š¬ Phase: Local Development - Testing with MCP Inspector
- š Next: Alpha Release - Publish to PyPI for Claude Desktop testing
- šÆ Future: Beta & v1.0 - Feature-complete and stable
See specs/ROADMAP.md for version planning.
Overview
This MCP server enables AI assistants to interact with Discord servers through tools for:
- ā Core Operations: List servers, channels, send messages
- ā Campaign System: Reaction-based opt-in campaigns with reminders
- š§ Future Features: Role management, member analytics, thread support, and more
Development Setup
Prerequisites
- Python 3.10+ with
uvpackage manager - Discord Bot: Create at Discord Developer Portal
- Node.js (for MCP Inspector)
Installation
# Clone repository
git clone https://github.com/yourusername/mcp-discord.git
cd mcp-discord
# Install with uv
uv pip install -e ".[dev]"
Configuration
Create a .env file:
DISCORD_TOKEN=your_discord_bot_token_here
MCP_DISCORD_DB_PATH=discord_mcp.db
LOG_LEVEL=INFO
DRY_RUN=false # Set to true for testing without Discord API
Testing with MCP Inspector
The MCP Inspector lets you test tools locally before deploying.
1. Start the MCP Inspector
npx @modelcontextprotocol/inspector python -m discord_mcp
This will:
- Start your Discord MCP server
- Launch the MCP Inspector web UI
- Open in your browser (usually http://localhost:5173)
2. Test Available Tools
In the inspector, you can test:
discord_list_servers- See all servers your bot is indiscord_list_channels- List channels in a serverdiscord_send_message- Send test messagesdiscord_create_campaign- Create reaction campaigns- And more...
3. Alternative: Direct Module Run
# Run server directly (for stdio transport)
python -m discord_mcp
# Run with development script
python dev.py server
# Run with inspector mode
python dev.py inspector
Claude Desktop Configuration (Alpha/Beta Only)
ā ļø Not ready yet - First test locally with inspector, then we'll publish to PyPI
Once published to PyPI, you can configure Claude Desktop:
Windows: Edit %APPDATA%\Claude\claude_desktop_config.json
Mac: Edit ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"discord": {
"command": "python",
"args": ["-m", "discord_mcp"],
"env": {
"DISCORD_TOKEN": "your_token_here",
"MCP_DISCORD_DB_PATH": "C:\\path\\to\\discord_mcp.db",
"LOG_LEVEL": "INFO"
}
}
}
}
Restart Claude Desktop to load the server.
Available Tools (v0.0.1-alpha)
Core Discord Tools
discord_list_servers- List all Discord serversdiscord_list_channels- List channels with type filteringdiscord_get_channel_info- Get detailed channel informationdiscord_bot_status- Check bot connection statusdiscord_get_recent_messages- Retrieve recent messagesdiscord_get_message- Get specific message by IDdiscord_send_message- Send messages with reply support
Campaign & Reminder Tools
discord_create_campaign- Create reaction opt-in campaignsdiscord_tally_optins- Track campaign participantsdiscord_list_optins- List opt-ins with paginationdiscord_build_reminder- Build reminder messagesdiscord_send_reminder- Send reminders with rate limitingdiscord_run_due_reminders- Process scheduled reminders
See specs/implemented/core_tools.md for detailed documentation.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
DISCORD_TOKEN |
Yes | - | Discord bot token |
MCP_DISCORD_DB_PATH |
No | discord_mcp.db |
SQLite database path |
GUILD_ALLOWLIST |
No | - | Comma-separated server IDs to restrict access |
LOG_LEVEL |
No | INFO |
Logging level (DEBUG, INFO, WARNING, ERROR) |
DRY_RUN |
No | false |
Test mode without Discord API calls |
Development Commands
# Run tests
uv run pytest
# Format code
uv run black src/ tests/
uv run isort src/ tests/
# Build package
uv build
# Run MCP inspector
npx @modelcontextprotocol/inspector python -m discord_mcp
Project Structure
discord-mcp/
āāā src/discord_mcp/ # Main package
ā āāā server.py # MCP server entry point
ā āāā __main__.py # Module runner (python -m discord_mcp)
ā āāā config.py # Configuration
ā āāā discord_client/ # Discord bot implementation
ā āāā database/ # SQLite models & repos
ā āāā tools/ # MCP tool implementations
ā āāā server_registry/ # Legacy entity registry
āāā tests/ # Test suite
āāā specs/ # Documentation
ā āāā implemented/ # Current features
ā āāā future/ # Planned features
ā āāā ROADMAP.md # Version roadmap
āāā pyproject.toml # Package configuration
āāā README.md # This file
Known Issues & Limitations
- ā ļø Alpha quality - Bugs expected
- ā ļø Limited features - Only basic tools implemented
- ā ļø No error recovery - Some edge cases not handled
- ā ļø Database migrations - Manual schema updates may be needed
See GitHub Issues for known bugs.
Contributing
This is an alpha project - contributions welcome but expect things to change!
- Test locally with MCP Inspector first
- Check specs/ROADMAP.md for planned features
- Open an issue to discuss changes
- Submit PR against
developbranch
Release Stages
- Now (Local): Testing with MCP Inspector only
- Alpha (0.0.x): Published to PyPI, testing with Claude Desktop
- Beta (0.1.x): Feature-complete, polishing bugs
- Release (1.0.0): Stable, production-ready
License
MIT License - see LICENSE file.
Support
- š Documentation: specs/ directory
- š Bug Reports: GitHub Issues
- š¬ Discussions: GitHub Discussions
Remember: This is alpha software. Always test in a non-production Discord server first!
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.