SLACKMCP Server

The Slack MCP Server lets your AI agent read and write messages in your Slack workspace. Useful for cross-referencing channel discussions with your code, notifying your team about deployments, or catching up on conversations you missed.

What you can do:

• Read channels — pull recent messages, catch up on discussions
• Post messages — send updates, announcements, and status reports
• Thread management — reply in context, keep conversations organized
• Search — find specific messages, topics, or mentions across your workspace

Setup

1. Create a Slack app at api.slack.com/apps
2. Add Bot Token scopes: channels:read, channels:history, chat:write, users:read
3. Install the app to your workspace and copy the Bot User OAuth Token
4. Add the server to your MCP config with the SLACK_BOT_TOKEN environment variable
5. Run npx @anthropic/mcp-server-slack to test

Note: Cursor and Windsurf support is limited — verify functionality on those clients.

Example prompts

"Read the last 20 messages in #engineering-incidents and summarize the database outage."

"Post to #deployments: 'v2.4.1 shipped — includes the cart fix and rate limiter update.'"

"Find the thread in #backend about Redis caching and reply with the approach from our code review."