How to Connect Slack to AI Agents with the Slack MCP Server

Integrate Slack with your AI agent using MCP. Read messages, post updates, manage channels, and automate Slack workflows.

Slackmessagingteam communicationautomationworkspace

Connect Slack to AI Agents with MCP

The Slack MCP server enables AI agents to interact with your Slack workspace — reading channels, posting messages, and managing conversations.

Prerequisites

▸Slack workspace admin access
▸
A Slack Bot Token (
code
```
xoxb-...
```
)
▸Node.js 18+

Creating a Slack Bot Token

▸Visit api.slack.com/apps
▸Click Create New App → From scratch
▸
Under OAuth & Permissions, add these Bot Token Scopes:
- ▸
  code
  channels:history
  — Read channel messages
- ▸
  code
  channels:read
  — List channels
- ▸
  code
  chat:write
  — Post messages
- ▸
  code
  users:read
  — View user info
- ▸
  code
  reactions:write
  — Add reactions
▸Install the app to your workspace
▸Copy the Bot User OAuth Token

Configuration

json

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-slack"],
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-token-here",
        "SLACK_TEAM_ID": "T0123456789"
      }
    }
  }
}

Available Tools

▸
code
```
list_channels
```
— Browse workspace channels
▸
code
```
post_message
```
— Send messages to channels
▸
code
```
reply_to_thread
```
— Reply in message threads
▸
code
```
add_reaction
```
— React to messages with emoji
▸
code
```
get_channel_history
```
— Read recent messages
▸
code
```
get_thread_replies
```
— Read thread conversations
▸
code
```
search_messages
```
— Full-text search across workspace
▸
code
```
get_users
```
— List workspace members
▸
code
```
get_user_profile
```
— Get user details

Example Workflows

Daily Standup Summary

code

"Summarize today's messages in the #engineering channel and highlight action items"

Cross-Channel Analysis

code

"Search for all mentions of 'deployment' across channels in the last week and create a summary"

Automated Responses

code

"Post a message to #general summarizing the key decisions from #leadership-sync"

Best Practices

▸Principle of least privilege: Only grant the scopes your use case requires
▸Audit bot actions: Monitor what the bot posts
▸Use threads: Reply in threads to avoid flooding channels
▸Rate limiting: Slack has API rate limits; the server handles retries automatically