Complete AI Training

MCP server · Productivity

Slack MCP server

by jtalk22

Let your AI read your Slack DMs, channels, threads and search results, and reply for you when you approve.

Flow diagram: you ask your AI “What blew up in #incidents overnight?”, the Slack MCP server connects it to Slack, and you get back A clear answer in your AI chat.

This is a small helper that connects your AI assistant to your own Slack account. Once it is set up, you can ask your AI things like what happened overnight in a channel, and it will actually go and read Slack for you. It is handy for anyone who comes back to a wall of unread messages and wants a quick summary instead of scrolling.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. It cannot see your Slack, because it has no way in. An MCP server is a little helper program that gives your AI a new skill, and in this case the skill is talking to Slack. You install this helper once, and from then on your AI can look things up in Slack or send a message when you ask it to.

What this MCP server does

You ask your AI a question about Slack, like what blew up overnight or what is waiting in a channel. Your AI passes that request to this helper program running on your computer. The helper uses the Slack login that is already saved in your Chrome browser, so there is no separate Slack app to create and no admin to ask. It fetches the messages, threads, or search results and hands them back to your AI. Your AI then reads them and gives you a summary or an answer in the chat.

Flow diagram: you ask your AI “What blew up in #incidents overnight?”, the Slack MCP server connects it to Slack, and you get back A clear answer in your AI chat. Click to zoom

What you can do with it

  • Catch up on unread channels and DMs without reading them yourself
  • Search your whole Slack workspace for a word or topic
  • Read a full thread and summarize what was decided
  • Export a channel's complete history with all its threads
  • Look up who a person is by name or email
  • Send a reply to a channel or DM when you approve it
  • Add or remove an emoji reaction and mark conversations as read

Try asking your AI

  • “What blew up in #incidents overnight? Give me the owner and the resolution.”
  • “Summarize my unread DMs from this morning.”
  • “Search Slack for anything about the printer PIN in #facilities.”
  • “Read the thread on the launch announcement and tell me what people are worried about.”

What it gives back to you

You get back plain answers in the chat: summaries, lists of messages, thread contents, or search results your AI has already read through. If you ask it to send something or add a reaction, it will tell you what it did. You do not get raw data dumps unless you ask for them.

Before you start

What you need

  • Node.js version 20 or newer (22 or 24 recommended)
  • Google Chrome with you signed in to Slack, on macOS for the automatic setup
  • On Windows or Linux, a Slack token and cookie that you paste into your client settings

Good to know

It can send messages, add reactions, and mark things as read in your Slack, so only approve those actions when you mean them, and be aware that on large company Slack setups this kind of browser login can get your session flagged.

Install it with your AI

Add Slack MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Slack MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Anyone who lives in Slack all day and wants their AI to read and summarize it for them, especially people in support, operations, or engineering who come back to a flood of messages.