This project includes code originally developed by Anthropic and released under the MIT License. Substantial modifications and new functionality have been added by For Good AI Inc. (dba Zencoder Inc.), and are licensed under the Apache License, Version 2.0.
A Model Context Protocol (MCP) server for interacting with Slack workspaces. This server provides tools to list channels, post messages, reply to threads, add reactions, get channel history, and manage users.
-
slack_list_channels
- List public or pre-defined channels in the workspace
- Optional inputs:
limit
(number, default: 100, max: 200): Maximum number of channels to returncursor
(string): Pagination cursor for next page
- Returns: List of channels with their IDs and information
-
slack_post_message
- Post a new message to a Slack channel
- Required inputs:
channel_id
(string): The ID of the channel to post totext
(string): The message text to post
- Returns: Message posting confirmation and timestamp
-
slack_reply_to_thread
- Reply to a specific message thread
- Required inputs:
channel_id
(string): The channel containing the threadthread_ts
(string): Timestamp of the parent messagetext
(string): The reply text
- Returns: Reply confirmation and timestamp
-
slack_add_reaction
- Add an emoji reaction to a message
- Required inputs:
channel_id
(string): The channel containing the messagetimestamp
(string): Message timestamp to react toreaction
(string): Emoji name without colons
- Returns: Reaction confirmation
-
slack_get_channel_history
- Get recent messages from a channel
- Required inputs:
channel_id
(string): The channel ID
- Optional inputs:
limit
(number, default: 10): Number of messages to retrieve
- Returns: List of messages with their content and metadata
-
slack_get_thread_replies
- Get all replies in a message thread
- Required inputs:
channel_id
(string): The channel containing the threadthread_ts
(string): Timestamp of the parent message
- Returns: List of replies with their content and metadata
-
slack_get_users
- Get list of workspace users with basic profile information
- Optional inputs:
cursor
(string): Pagination cursor for next pagelimit
(number, default: 100, max: 200): Maximum users to return
- Returns: List of users with their basic profiles
-
slack_get_user_profile
- Get detailed profile information for a specific user
- Required inputs:
user_id
(string): The user's ID
- Returns: Detailed user profile information
To use this MCP server, you need to create a Slack app and configure it with the necessary permissions:
- Visit the Slack Apps page
- Click "Create New App"
- Choose "From scratch"
- Name your app and select your workspace
Navigate to "OAuth & Permissions" and add these scopes:
channels:history
- View messages and other content in public channelschannels:read
- View basic channel informationchat:write
- Send messages as the appreactions:write
- Add emoji reactions to messagesusers:read
- View users and their basic informationusers.profile:read
- View detailed profiles about users
- Click "Install to Workspace" and authorize the app
- Save the "Bot User OAuth Token" that starts with
xoxb-
Get your Team ID (starts with a T
) by following this guidance
For the bot to access private channels or to post messages, you may need to invite it to specific channels using /invite @your-bot-name
- Multiple Transport Support: Supports both stdio and Streamable HTTP transports
- Modern MCP SDK: Updated to use the latest MCP SDK (v1.13.2) with modern APIs
- Comprehensive Slack Integration: Full set of Slack operations including:
- List channels (with predefined channel support)
- Post messages
- Reply to threads
- Add reactions
- Get channel history
- Get thread replies
- List users
- Get user profiles
npm install
npm run build
npm install -g @zencoderai/slack-mcp-server
# Build the Docker image locally
docker build -t slack-mcp-server .
# Or pull from Docker Hub
docker pull zencoderai/slack-mcp:latest
# Or pull a specific version
docker pull zencoderai/slack-mcp:1.0.0
Set the following environment variables:
export SLACK_BOT_TOKEN="xoxb-your-bot-token"
export SLACK_TEAM_ID="your-team-id"
export SLACK_CHANNEL_IDS="channel1,channel2,channel3" # Optional: predefined channels
export AUTH_TOKEN="your-auth-token" # Optional: Bearer token for HTTP authorization (Streamable HTTP transport only)
slack-mcp [options]
Options:
--transport <type> Transport type: 'stdio' or 'http' (default: stdio)
--port <number> Port for HTTP server when using Streamable HTTP transport (default: 3000)
--token <token> Bearer token for HTTP authorization (optional, can also use AUTH_TOKEN env var)
--help, -h Show this help message
# Use stdio transport (default)
slack-mcp
# Use stdio transport explicitly
slack-mcp --transport stdio
# Use Streamable HTTP transport on default port 3000
slack-mcp --transport http
# Use Streamable HTTP transport on custom port
slack-mcp --transport http --port 8080
# Use Streamable HTTP transport with custom auth token
slack-mcp --transport http --token mytoken
# Use Streamable HTTP transport with auth token from environment variable
AUTH_TOKEN=mytoken slack-mcp --transport http
# Use stdio transport (default)
node dist/index.js
# Use stdio transport explicitly
node dist/index.js --transport stdio
# Use Streamable HTTP transport on default port 3000
node dist/index.js --transport http
# Use Streamable HTTP transport on custom port
node dist/index.js --transport http --port 8080
# Use Streamable HTTP transport with custom auth token
node dist/index.js --transport http --token mytoken
# Use Streamable HTTP transport with auth token from environment variable
AUTH_TOKEN=mytoken node dist/index.js --transport http
# Run with stdio transport (default)
docker run --rm \
-e SLACK_BOT_TOKEN="xoxb-your-bot-token" \
-e SLACK_TEAM_ID="your-team-id" \
zencoderai/slack-mcp:latest
# Run with HTTP transport on port 3000
docker run --rm -p 3000:3000 \
-e SLACK_BOT_TOKEN="xoxb-your-bot-token" \
-e SLACK_TEAM_ID="your-team-id" \
zencoderai/slack-mcp:latest --transport http
# Run with HTTP transport on custom port
docker run --rm -p 8080:8080 \
-e SLACK_BOT_TOKEN="xoxb-your-bot-token" \
-e SLACK_TEAM_ID="your-team-id" \
zencoderai/slack-mcp:latest --transport http --port 8080
# Run with custom auth token
docker run --rm -p 3000:3000 \
-e SLACK_BOT_TOKEN="xoxb-your-bot-token" \
-e SLACK_TEAM_ID="your-team-id" \
-e AUTH_TOKEN="mytoken" \
zencoderai/slack-mcp:latest --transport http
Create a docker-compose.yml
file:
version: '3.8'
services:
slack-mcp:
# Use published image:
image: zencoderai/slack-mcp:latest
# Or build locally:
# build: .
environment:
- SLACK_BOT_TOKEN=xoxb-your-bot-token
- SLACK_TEAM_ID=your-team-id
- SLACK_CHANNEL_IDS=channel1,channel2,channel3 # Optional
- AUTH_TOKEN=your-auth-token # Optional for HTTP transport
ports:
- "3000:3000" # Only needed for HTTP transport
command: ["--transport", "http"] # Optional: specify transport type
restart: unless-stopped
Then run:
# Start the service
docker compose up -d
# View logs
docker compose logs -f slack-mcp
# Stop the service
docker compose down
- Use case: Command-line tools and direct integrations
- Communication: Standard input/output streams
- Default: Yes
- Use case: Remote servers and web-based integrations
- Communication: HTTP POST requests with optional Server-Sent Events streams
- Features:
- Session management
- Bidirectional communication
- Resumable connections
- RESTful API endpoints
- Bearer token authentication
When using Streamable HTTP transport, the server supports Bearer token authentication:
- Command Line: Use
--token <token>
to specify a custom token - Environment Variable: Set
AUTH_TOKEN=<token>
as a fallback - Auto-generated: If neither is provided, a random token is generated
The command line option takes precedence over the environment variable. Include the token in HTTP requests using the Authorization: Bearer <token>
header.
If you encounter permission errors, verify that:
- All required scopes are added to your Slack app
- The app is properly installed to your workspace
- The tokens and workspace ID are correctly copied to your configuration
- The app has been added to the channels it needs to access
npm run build
npm run watch
When using Streamable HTTP transport, the server exposes the following endpoints:
POST /mcp
- Client-to-server communicationGET /mcp
- Server-to-client notifications (Server-Sent Events streams)DELETE /mcp
- Session termination
- Updated MCP SDK: Upgraded from v1.0.1 to v1.13.2
- Modern API: Migrated from low-level Server class to high-level McpServer class
- Zod Validation: Added proper schema validation using Zod
- Transport Flexibility: Added support for Streamable HTTP transport
- Command Line Interface: Added CLI arguments for transport selection
- Session Management: Implemented proper session handling for HTTP transport
- Better Error Handling: Improved error handling and logging