A MCP(Model Context Protocol) server for accessing Slack API. This server allows AI assistants to interact with the Slack API through a standardized interface.
This server supports both traditional and modern MCP transport methods:
- Stdio Transport (default): Process-based communication for local integration
- Streamable HTTP Transport: HTTP-based communication for web applications and remote clients
Available tools:
slack_list_channels- List public channels in the workspace with paginationslack_post_message- Post a new message to a Slack channelslack_reply_to_thread- Reply to a specific message thread in Slackslack_add_reaction- Add a reaction emoji to a messageslack_get_channel_history- Get recent messages from a channelslack_get_thread_replies- Get all replies in a message threadslack_get_users- Retrieve basic profile information of all users in the workspaceslack_get_user_profile- Get a user's profile informationslack_get_user_profiles- Get multiple users' profile information in bulk (efficient for batch operations)slack_search_messages- Search for messages in the workspace
npm install @ubie-oss/slack-mcp-serverNOTE: Its now hosted in GitHub Registry so you need your PAT.
You need to set the following environment variables:
SLACK_BOT_TOKEN: Slack Bot User OAuth TokenSLACK_USER_TOKEN: Slack User OAuth Token (required for some features like message search)
You can also create a .env file to set these environment variables:
SLACK_BOT_TOKEN=xoxb-your-bot-token
SLACK_USER_TOKEN=xoxp-your-user-token
Stdio Transport (default):
npx @ubie-oss/slack-mcp-serverStreamable HTTP Transport:
npx @ubie-oss/slack-mcp-server -port 3000You can also run the installed module with node:
# Stdio transport
node node_modules/.bin/slack-mcp-server
# HTTP transport
node node_modules/.bin/slack-mcp-server -port 3000Command Line Options:
-port <number>: Start with Streamable HTTP transport on specified port-h, --help: Show help message
For Stdio Transport (Claude Desktop, etc.):
{
"slack": {
"command": "npx",
"args": [
"-y",
"@ubie-oss/slack-mcp-server"
],
"env": {
"NPM_CONFIG_//npm.pkg.github.com/:_authToken": "<your-github-pat>",
"SLACK_BOT_TOKEN": "<your-bot-token>",
"SLACK_USER_TOKEN": "<your-user-token>"
}
}
}For Streamable HTTP Transport (Web applications):
Start the server:
SLACK_BOT_TOKEN=<your-bot-token> SLACK_USER_TOKEN=<your-user-token> npx @ubie-oss/slack-mcp-server -port 3000Connect to: http://localhost:3000/mcp
See examples/README.md for detailed client examples.
This server adopts the following implementation pattern:
-
Define request/response using Zod schemas
- Request schema: Define input parameters
- Response schema: Define responses limited to necessary fields
-
Implementation flow:
- Validate request with Zod schema
- Call Slack WebAPI
- Parse response with Zod schema to limit to necessary fields
- Return as JSON
For example, the slack_list_channels implementation parses the request with ListChannelsRequestSchema, calls slackClient.conversations.list, and returns the response parsed with ListChannelsResponseSchema.
npm run dev- Start the server in development mode with hot reloadingnpm run build- Build the project for productionnpm run start- Start the production servernpm run lint- Run linting checks (ESLint and Prettier)npm run fix- Automatically fix linting issues
- Fork the repository
- Create your feature branch
- Run tests and linting:
npm run lint - Commit your changes
- Push to the branch
- Create a Pull Request