NativeAIHub
Slack MCP Server

Slack MCP Server

Connect your AI agent to Slack. Read channels, search conversations, post messages, manage threads, and turn team discussions into structured action items.

MCP Server·3 sections·1 min read
productivityworkflow
Install Prompt

Paste this into Claude Code to set it up:

I want to add the Slack MCP Server to my Claude Code setup.

IMPORTANT: Never use Read/Edit tools on ~/.claude.json. Use jq via Bash instead.

Prerequisites: You need a Slack Bot Token (starts with xoxb-). To get one:
1. Go to api.slack.com/apps and click "Create New App" > "From scratch"
2. Under OAuth and Permissions, add scopes: channels:history, channels:read, chat:write, groups:history, groups:read, search:read, users:read
3. Install the app to your workspace and copy the Bot User OAuth Token

Run this command to add the MCP server (replace xoxb-your-token with your actual token):
```bash
jq '.mcpServers["slack"] = {"type": "stdio", "command": "npx", "args": ["-y", "@anthropic/slack-mcp"], "env": {"SLACK_BOT_TOKEN": "xoxb-your-token"}}' ~/.claude.json > /tmp/claude-json-tmp && mv /tmp/claude-json-tmp ~/.claude.json
```

After adding, restart Claude Code. Remember to invite the bot to any channels it should access with /invite @your-bot-name in Slack.

01What It Does

The input layer for your entire workflow

Slack MCP closes the loop between conversation and action. Discussions about bugs become GitHub issues. Decisions from threads become Notion pages. Action items become Todoist tasks. Instead of scrolling through dozens of channels to catch up, the agent reads everything and gives you the summary.
📖
Read and SearchAccess messages from any channel the bot is in. Search across your entire workspace history to find specific discussions and decisions.
✉️
Post and ReplySend messages to channels or threads. Post deploy notifications, status updates, or follow ups, all formatted consistently.

02Real Scenarios

1

"Summarize #engineering today"

The agent reads all messages, identifies key discussions and decisions, and provides a structured summary in 30 seconds instead of 15 minutes of scrolling.

2

"What happened while I was on PTO?"

The agent reads your key channels from the past week, filters noise, and creates a digest of important discussions and anything mentioning you.

3

"Create tasks from the standup thread"

The agent reads the standup thread, extracts blockers and commitments, and creates prioritized tasks in Todoist for each action item.

4

"Post the deploy notification to #releases"

After a deployment, the agent posts a formatted message with version number, changes included, and relevant links.

03Setup

1

Create a Slack App

Go to api.slack.com/apps, click "Create New App," choose "From scratch," and select your workspace.

2

Add Bot Token Scopes

Under OAuth and Permissions, add: channels:history, channels:read, chat:write, groups:history, groups:read, search:read, users:read.

3

Install and Copy Token

Install the app to your workspace. Copy the Bot User OAuth Token (starts with xoxb-).

4

Invite the Bot

In Slack, invite the bot to channels it should access with /invite @your-bot-name.

# Add to ~/.claude.json under mcpServers
"slack": {
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "@anthropic/slack-mcp"],
  "env": { "SLACK_BOT_TOKEN": "xoxb-your-token" }
}