Slack Integration MCP Server

Overview

The Slack Integration MCP server provides a bridge between AI assistants and your Slack workspace. With this integration, AI assistants can view channel messages, post new content, reply to threads, add emoji reactions, and access user information.

Prerequisites

Before setting up the Slack Integration, you'll need to:

1. Have a Slack workspace where you have permissions to add applications
2. Create a Slack App with appropriate permissions
3. Install Node.js or Docker on your system (depending on your preferred installation method)

Creating a Slack App

1. Visit the Slack API Apps page
2. Click "Create New App" and select "From scratch"
3. Name your app and select your workspace
4. Navigate to "OAuth & Permissions" and add the following Bot Token Scopes:
   • channels:history - View messages in public channels
   • channels:read - View basic channel information
   • chat:write - Send messages as the app
   • reactions:write - Add emoji reactions to messages
   • users:read - View users and their basic information
   • users.profile:read - View detailed user profiles
5. Install the app to your workspace and authorize it
6. Save the "Bot User OAuth Token" that starts with xoxb-
7. Get your Team ID (starts with a T) from your Slack URL or workspace settings

Installation Options

Using NPX

The simplest way to run the Slack Integration is using NPX, which will automatically download and run the package:

npx -y @modelcontextprotocol/server-slack

Using Docker

You can also run the integration using Docker:

docker run -i --rm mcp/slack

Configuration

The Slack Integration requires the following environment variables:

• SLACK_BOT_TOKEN: Your Bot User OAuth Token (starts with xoxb-)
• SLACK_TEAM_ID: Your Slack Team ID (starts with T)
• SLACK_CHANNEL_IDS (optional): Comma-separated list of specific channel IDs to access

Usage with Claude Desktop

Add the following configuration to your claude_desktop_config.json file:

NPX Configuration

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-slack"
      ],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-bot-token",
        "SLACK_TEAM_ID": "T01234567",
        "SLACK_CHANNEL_IDS": "C01234567, C76543210"
      }
    }
  }
}

Docker Configuration

{
  "mcpServers": {
    "slack": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SLACK_BOT_TOKEN",
        "-e",
        "SLACK_TEAM_ID",
        "-e",
        "SLACK_CHANNEL_IDS",
        "mcp/slack"
      ],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-bot-token",
        "SLACK_TEAM_ID": "T01234567",
        "SLACK_CHANNEL_IDS": "C01234567, C76543210"
      }
    }
  }
}

Usage with VS Code

For VS Code users, you can install the Slack Integration directly through the editor:

1. Press Ctrl + Shift + P to open the command palette
2. Type Preferences: Open Settings (JSON) and select it
3. Add the appropriate configuration block to your settings file

Alternatively, you can create a .vscode/mcp.json file in your workspace with the configuration.

Troubleshooting

If you encounter issues with the Slack Integration:

1. Verify your Bot Token has the correct permissions
2. Ensure your app is properly installed to your workspace
3. Check that the environment variables are correctly set
4. Confirm the bot has been invited to the channels you're trying to access