Slack MCP Server

A production-ready Model Context Protocol (MCP) server for Slack workspace operations. Connect any AI agent to Slack — send messages, manage channels, search conversations, react to messages, upload files, and look up user profiles.

This is an independent, generalized MCP server. It is not tied to any specific project and can be connected to any AI agent that supports MCP (Claude Desktop, Cursor, WorkOS, or custom agents).

Features

• 📨 Messaging: Send messages, read channels, reply to threads, send DMs
• 📁 Channels: List, create, archive channels, set topics
• 🔍 Search: Full-text search across workspace messages
• 😀 Reactions: Add/remove emoji reactions, pin/unpin messages
• 👤 Users: Look up user profiles (name, email, title, status)
• 📎 Files: Upload text files to channels

Installation

Recommended — no pre-install required (uses uv):

# uv manages a temporary isolated environment automatically
uvx --from workos-slack-mcp-server slack-mcp-server

Or install permanently with pip:

pip install workos-slack-mcp-server

Or install from source:

git clone https://github.com/workos/workos-slack-mcp-server
cd workos-slack-mcp-server
pip install -e .

Quick Start

export SLACK_BOT_TOKEN="xoxb-your-bot-token"
export SLACK_USER_TOKEN="xoxp-your-user-token"      # Optional, for search
export SLACK_SIGNING_SECRET="your-signing-secret"    # Optional, for verification

# Recommended: run via uvx (no install needed)
uvx --from workos-slack-mcp-server slack-mcp-server

# Or if installed via pip
slack-mcp-server

# Or run as a Python module
python -m slack_mcp_server

Configuration

Environment Variables

Variable	Required	Description
SLACK_BOT_TOKEN	✅ Yes	Bot User OAuth Token (xoxb-...)
SLACK_USER_TOKEN	⬜ No	User OAuth Token (xoxp-...) — enables broader search results
SLACK_SIGNING_SECRET	⬜ No	App Signing Secret — for request verification

Getting Slack Tokens

1. Go to api.slack.com/apps and create a new app
2. Under OAuth & Permissions, add Bot Token Scopes:
   • channels:read, channels:write, channels:history
   • chat:write, chat:write.public
   • reactions:read, reactions:write
   • pins:read, pins:write
   • users:read, users:read.email
   • files:read, files:write
   • search:read (user token scope)
   • im:write, im:read
3. Install the app to your workspace
4. Copy the Bot User OAuth Token (xoxb-...)
5. Copy the User OAuth Token (xoxp-...)
6. Copy the Signing Secret from Basic Information page

Connecting to AI Agents

Note: Use uvx --from workos-slack-mcp-server slack-mcp-server in all configs below. The --from flag is needed because the PyPI package name (workos-slack-mcp-server) differs from the CLI entry point (slack-mcp-server). You must have uv installed (brew install uv on macOS).

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "slack": {
      "command": "uvx",
      "args": ["--from", "workos-slack-mcp-server", "slack-mcp-server"],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-token",
        "SLACK_USER_TOKEN": "xoxp-your-token",
        "SLACK_SIGNING_SECRET": "your-secret"
      }
    }
  }
}

Alternative — if you have installed via pip install workos-slack-mcp-server and prefer not to use uvx, use the full absolute path to the binary instead:

{ "command": "/path/to/your/bin/slack-mcp-server" }

Find the path with: which slack-mcp-server

Cursor

Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "slack": {
      "command": "uvx",
      "args": ["--from", "workos-slack-mcp-server", "slack-mcp-server"],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-token",
        "SLACK_USER_TOKEN": "xoxp-your-token",
        "SLACK_SIGNING_SECRET": "your-secret"
      }
    }
  }
}

VS Code (GitHub Copilot / MCP extension)

Edit .vscode/mcp.json in your project:

{
  "servers": {
    "slack": {
      "type": "stdio",
      "command": "uvx",
      "args": ["--from", "workos-slack-mcp-server", "slack-mcp-server"],
      "env": {
        "SLACK_BOT_TOKEN": "${input:slackBotToken}"
      }
    }
  },
  "inputs": [
    {
      "id": "slackBotToken",
      "type": "promptString",
      "description": "Slack Bot Token (xoxb-...)",
      "password": true
    }
  ]
}

WorkOS / Custom Agents

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "slack": {
      "transport": "stdio",
      "command": "uvx",
      "args": ["--from", "workos-slack-mcp-server", "slack-mcp-server"],
      "env": {
        "SLACK_BOT_TOKEN": "${SLACK_BOT_TOKEN}",
        "SLACK_USER_TOKEN": "${SLACK_USER_TOKEN}",
        "SLACK_SIGNING_SECRET": "${SLACK_SIGNING_SECRET}"
      }
    }
  }
}

Available Tools (15)

Tool	Description
slack_send_message	Send a message to a channel
slack_read_messages	Read recent messages from a channel
slack_reply_thread	Reply to a message thread
slack_send_dm	Send a direct message to a user
slack_list_channels	List workspace channels
slack_create_channel	Create a new channel
slack_archive_channel	Archive a channel
slack_set_channel_topic	Set channel topic
slack_search_messages	Search messages across workspace
slack_add_reaction	Add emoji reaction to a message
slack_remove_reaction	Remove emoji reaction
slack_pin_message	Pin a message in a channel
slack_unpin_message	Unpin a message
slack_get_user_profile	Get user profile information
slack_upload_file	Upload a text file to a channel

Development

git clone https://github.com/workos/workos-slack-mcp-server
cd workos-slack-mcp-server
pip install -e .

# Run tests
pytest

# Run the server locally
SLACK_BOT_TOKEN=xoxb-... python -m slack_mcp_server

Publishing

To PyPI

pip install build twine
rm -rf dist/ build/ src/*.egg-info
python -m build
pip install "packaging>=24.2"   # required for Metadata 2.4 support in twine
twine check dist/*              # validate before uploading
twine upload dist/*

To MCP Registry

mcp-publisher login github
mcp-publisher publish

License

MIT — see LICENSE for details.