Slack MCP

v1.3.0Communicationstable

A Message Control Protocol server that integrates with Slack to provide channel management, messaging capabilities, and log monitoring across multiple servers, enabling teams to share logs and receive automated alerts in Slack channels.

assistantsgovslackllmmcpmcp-server
Share:
1,618
Stars
0
Downloads
0
Weekly
0/5

What is Slack MCP?

Slack MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to message control protocol server that integrates with slack to provide channel management, messaging capabilities, and log monitoring across multiple servers, enabling teams to share logs and receive a...

A Message Control Protocol server that integrates with Slack to provide channel management, messaging capabilities, and log monitoring across multiple servers, enabling teams to share logs and receive automated alerts in Slack channels.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Message Control Protocol server that integrates with Slack

Use Cases

Channel management and messaging automation
Log monitoring and alerts in Slack
korotovsky

Maintainer

LicenseMIT License
Languagego
Versionv1.3.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y slack-mcp-server

Manual Installation

npx -y slack-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Slack MCP

Slack MCP Server is a Go-based Model Context Protocol server that connects AI assistants to a Slack workspace, enabling them to read channel history, search messages, manage user groups, post messages, and add emoji reactions. It supports multiple authentication methods including user OAuth tokens, bot tokens, and browser session tokens, and gates write operations (posting, reacting, marking read) behind explicit opt-in environment variables for safety. DevOps teams and developers use it to let AI assistants monitor Slack conversations, surface relevant discussions, send automated alerts, and build log-monitoring workflows across multiple servers that report into Slack channels.

Prerequisites

  • A Slack workspace where you have sufficient permissions to create an app or extract tokens
  • At least one Slack authentication token: SLACK_MCP_XOXP_TOKEN (user OAuth), SLACK_MCP_XOXB_TOKEN (bot), or SLACK_MCP_XOXC_TOKEN + SLACK_MCP_XOXD_TOKEN (browser session)
  • Node.js 18+ (for the npx-based install) or Go 1.21+ (for building from source)
  • An MCP-compatible AI client: Claude Desktop, Cursor, or similar
1

Obtain a Slack authentication token

The recommended approach is a user OAuth token (xoxp-...) from a Slack app with channels:history, channels:read, users:read, and search:read scopes. Alternatively, use a bot token (xoxb-...) for bot-level access, or browser session tokens (xoxc + xoxd) for direct workspace access without creating an app.

2

Configure the MCP server with your token

Add the Slack MCP server to your MCP client config, setting the appropriate token environment variable. Enable optional write tools only if needed by setting their flags to 'true'.

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "slack-mcp-server"],
      "env": {
        "SLACK_MCP_XOXP_TOKEN": "xoxp-your-user-oauth-token",
        "SLACK_MCP_ADD_MESSAGE_TOOL": "false",
        "SLACK_MCP_REACTION_TOOL": "false",
        "SLACK_MCP_MARK_TOOL": "false"
      }
    }
  }
}
3

Enable write capabilities if needed (optional)

To allow the AI to post messages, add reactions, or mark messages as read, set the corresponding environment variables to 'true'. These are disabled by default for safety.

"SLACK_MCP_ADD_MESSAGE_TOOL": "true",
"SLACK_MCP_REACTION_TOOL": "true",
"SLACK_MCP_MARK_TOOL": "true"
4

Restart your MCP client

Restart Claude Desktop or reload your editor's MCP extension. The server starts via npx and connects to your Slack workspace using the provided token.

5

Query Slack content through the AI assistant

Ask your AI assistant to retrieve channel history, search messages, list users, or summarize discussions. The server handles pagination and filtering automatically.

Slack MCP Examples

Client configuration

Claude Desktop config using a user OAuth token for read-only Slack access via the slack-mcp-server npm package.

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "slack-mcp-server"],
      "env": {
        "SLACK_MCP_XOXP_TOKEN": "xoxp-your-user-oauth-token",
        "SLACK_MCP_ADD_MESSAGE_TOOL": "false",
        "SLACK_MCP_REACTION_TOOL": "false"
      }
    }
  }
}

Prompts to try

These prompts demonstrate reading channels, searching messages, and managing user groups through the Slack MCP server.

- "Summarize the last 50 messages in the #engineering channel"
- "Search Slack for messages about the database outage from last Tuesday"
- "List all unread messages across my channels, sorted by priority"
- "Who are the members of the @backend-team user group?"
- "Show me the thread discussion in #deployments from the message about the v2.3.1 release"

Troubleshooting Slack MCP

Authentication error: token_expired or invalid_auth

User OAuth tokens (xoxp) can expire if the Slack app's token rotation is enabled. Regenerate the token in your Slack app's OAuth & Permissions page. For browser session tokens (xoxc/xoxd), these expire when your browser session ends — re-extract them from your browser's developer tools.

Channel history returns empty results or missing_scope error

Ensure your Slack app or token has the channels:history scope for public channels and groups:history for private channels. Bot tokens (xoxb) must be invited into each channel before they can read its history.

Message posting does not work even with SLACK_MCP_ADD_MESSAGE_TOOL set to true

Posting messages also requires the chat:write scope on your token. Bot tokens need to be invited to the target channel. Check the Slack app's OAuth scopes and ensure the token in your config has write permissions.

Frequently Asked Questions about Slack MCP

What is Slack MCP?

Slack MCP is a Model Context Protocol (MCP) server that message control protocol server that integrates with slack to provide channel management, messaging capabilities, and log monitoring across multiple servers, enabling teams to share logs and receive automated alerts in slack channels. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Slack MCP?

Install via npm with the command: npx -y slack-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Slack MCP?

Slack MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Slack MCP free to use?

Yes, Slack MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "slack-mcp": { "command": "npx", "args": ["-y", "slack-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Slack MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides