Slack MCP Server
Enables interaction with Slack workspaces through comprehensive integration capabilities. Supports channel management, messaging, thread replies, reactions, and message history retrieval through natural language commands.
README
Slack MCP Server
A Model Context Protocol (MCP) server that provides Slack integration capabilities. This server follows clean architecture principles with proper separation of concerns.
Features
- List Channels: Get all public channels in your workspace with pagination support
- Post Messages: Send messages to specific channels
- Reply to Threads: Reply to existing message threads
- Add Reactions: Add emoji reactions to messages
- Get Channel History: Retrieve recent messages from channels
- Get Thread Replies: Get all replies in a message thread
- Parse Slack URLs: Automatically extract thread details from Slack URLs
Architecture
This project follows clean architecture principles:
src/
├── core/ # Domain layer
│ ├── interfaces/ # Interfaces and contracts
│ └── types/ # Type definitions
├── application/ # Application layer
│ ├── services/ # Business logic services
│ └── usecases/ # Use case implementations
├── infrastructure/ # Infrastructure layer
│ ├── server/ # Mcp server configuration
│ ├── clients/ # External API clients
│ └── storage/ # Storage implementations
├── presentation/ # Presentation layer
│ └── routes/ # API routes (if needed)
└── config/ # Configuration and dependency injection
Setup
1. Slack App Configuration
First, create a Slack App and configure the required permissions:
-
Go to https://api.slack.com/apps
-
Create a new app or select existing one
-
Navigate to OAuth & Permissions → Bot Token Scopes
-
Add the following permissions:
channels:read - List channels channels:history - Read public channel messages groups:history - Read private channel/group messages chat:write - Send messages reactions:write - Add emoji reactions -
Click Install App to Workspace
-
Copy the Bot User OAuth Token (starts with
xoxb-)
2. Project Setup
-
Install dependencies:
npm install -
Build the project:
npm run build -
Run the server:
npm start
3. MCP Configuration
Add to your MCP client configuration (e.g., Cursor):
{
"slack-mcp": {
"url": "http://localhost:3001/sse",
"env": {
"SLACK_TOKEN": "xoxb-your-bot-token-here"
}
}
}
Development
- Development mode:
npm run dev - Inspector mode:
npm run inspector - Clean build:
npm run clean && npm run build
Token Management
All tools require a token parameter (Slack Bot Token). The token is passed directly to each tool call, ensuring secure and flexible authentication.
Example usage:
await slack_list_channels({
limit: 50,
token: "xoxb-your-bot-token-here",
});
Available Tools
slack_list_channels
List public channels in the workspace with pagination.
Parameters:
limit(optional): Maximum number of channels to return (default 100, max 200)cursor(optional): Pagination cursor for next page of resultstoken: Slack bot token (required)
slack_post_message
Post a new message to a Slack channel.
Parameters:
channel_id: The ID of the channel to post totext: The message text to posttoken: Slack bot token (required)
slack_reply_to_thread
Reply to a specific message thread in Slack.
Parameters:
channel_id: The ID of the channel containing the threadthread_ts: The timestamp of the parent messagetext: The reply texttoken: Slack bot token (required)
slack_add_reaction
Add a reaction emoji to a message.
Parameters:
channel_id: The ID of the channel containing the messagetimestamp: The timestamp of the message to react toreaction: The name of the emoji reaction (without ::)token: Slack bot token (required)
slack_get_channel_history
Get recent messages from a channel.
Parameters:
channel_id: The ID of the channellimit(optional): Number of messages to retrieve (default 10)token: Slack bot token (required)
slack_get_thread_replies
Get all replies in a message thread.
Parameters:
channel_id: The ID of the channel containing the threadthread_ts: The timestamp of the parent messagetoken: Slack bot token (required)
slack_parse_url
Parse a Slack URL and automatically extract thread/message details.
Parameters:
url: Slack URL (e.g., https://workspace.slack.com/archives/CHANNEL_ID/pTIMESTAMP)token: Slack bot token (required)
Example:
await slack_parse_url({
url: "https://workspace.slack.com/archives/CHANNEL_ID/pTIMESTAMP",
token: "xoxb-your-bot-token-here",
});
This tool automatically:
- Parses the URL to extract workspace, channel ID, and message timestamp
- Fetches channel history
- Retrieves thread replies if available
- Returns formatted message details
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.