pashpashpash

Discord MCP Server

Community pashpashpash
Updated

Discord integration for Model Context Protocol

Discord MCP Server

A Model Context Protocol (MCP) server that provides Discord integration capabilities to MCP clients like Claude Desktop.

Features

Server Information

  • get_server_info: Get detailed server information
  • list_members: List server members and their roles

Message Management

  • send_message: Send a message to a channel
  • read_messages: Read recent message history
  • add_reaction: Add a reaction to a message
  • add_multiple_reactions: Add multiple reactions to a message
  • remove_reaction: Remove a reaction from a message
  • moderate_message: Delete messages and timeout users

Channel Management

  • create_text_channel: Create a new text channel
  • delete_channel: Delete an existing channel

Role Management

  • add_role: Add a role to a user
  • remove_role: Remove a role from a user

Webhook Management

  • create_webhook: Create a new webhook
  • list_webhooks: List webhooks in a channel
  • send_webhook_message: Send messages via webhook
  • modify_webhook: Update webhook settings
  • delete_webhook: Delete a webhook

Prerequisites

  1. Set up your Discord bot:

    • Create a new application at Discord Developer Portal
    • Create a bot and copy the token
    • Enable required privileged intents:
      • MESSAGE CONTENT INTENT
      • PRESENCE INTENT
      • SERVER MEMBERS INTENT
    • Invite the bot to your server using OAuth2 URL Generator
  2. Python Requirements:

    • Python 3.8 or higher
    • pip (Python package installer)

Installation

  1. Clone the Repository:

    git clone https://github.com/pashpashpash/mcp-discord.git
    cd mcp-discord
    
  2. Create and Activate Virtual Environment:

    # On Windows
    python -m venv venv
    venv\Scripts\activate
    
    # On macOS/Linux
    python -m venv venv
    source venv/bin/activate
    
  3. Install Dependencies:

    pip install -e .
    

    Note: If using Python 3.13+, also install audioop: pip install audioop-lts

  4. Configure Claude Desktop:

Add this to your claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "discord": {
      "command": "python",
      "args": ["-m", "mcp_discord"],
      "cwd": "path/to/mcp-discord",
      "env": {
        "DISCORD_TOKEN": "your_bot_token"
      }
    }
  }
}

Note:

  • Replace "path/to/mcp-discord" with the actual path to your cloned repository
  • Replace "your_bot_token" with your Discord bot token

Debugging

If you run into issues, check Claude Desktop's MCP logs:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Common issues:

  1. Token Errors:

    • Verify your Discord bot token is correct
    • Check that all required intents are enabled
  2. Permission Issues:

    • Ensure the bot has proper permissions in your Discord server
    • Verify the bot's role hierarchy for role management commands
  3. Installation Issues:

    • Make sure you're using the correct Python version
    • Try recreating the virtual environment
    • Check that all dependencies are installed correctly

License

MIT License - see LICENSE file for details.

Note: This is a fork of the original mcp-discord repository.

MCP Server · Populars

MCP Server · New

    cognicore-dev

    CogniCore

    Persistent memory, reflection & safety for AI agents. No vector DB, no embedding server — BM25 + multi-hop retrieval runs in-process. MCP server with 10 tools. Apache 2.0.

    Community cognicore-dev
    avivgerz-hue

    🛡️ vibe-shield

    60-rule static security scanner, MCP server & skill poisoning auditor for AI-generated codebases (Claude Code, Codex, Cursor).

    Community avivgerz-hue
    frankShan001

    CutVoke

    Open-source, local-first video editor your AI agent can drive over MCP (Claude Code, Codex, Cursor). Windows · macOS · Linux. The AI makes the cut; you finish it on the same timeline.

    Community frankShan001
    HiveForensics-AI

    @knolo/mcp

    The open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.

    Community HiveForensics-AI
    shannonbay

    Quarterdeck

    Persistent goals for Claude Code, like "keep my inbox under control". Fresh agent runs on a schedule, webhook or failing health check, with instructions, memory and your decisions kept outside the agent. Actions wait for your approval until you trust them, enforced by a hook. MCP server + web app.

    Community shannonbay