Slack
Summary
Read and post to Slack from an AI client — channels, threads, reactions, and user lookup.
Features
- List channels and read conversation history
- Post messages and threaded replies
- Add reactions and look up user profiles
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
The Slack MCP server, now maintained by Zencoder after being retired from the MCP reference collection, connects an assistant to a Slack workspace.
What it can do
- List channels the bot has access to
- Read history from a channel or a thread, which is what makes summarising a long discussion possible
- Post messages and reply in threads
- Add reactions
- Look up users and their profiles
Realistic uses
Summarising what happened in a channel while you were away; pulling the decision out of a forty-message thread; posting a build or deploy notification from an agent workflow; and answering questions about past discussions without scrolling.
Setup and permissions
Requires a Slack bot token with scopes matched to what you want it to do, plus the workspace team ID. Scope it narrowly — a bot with channels:history across an entire workspace is a broader grant than most people intend, and the assistant will read whatever it can reach.
Runs with npx -y @zencoderai/slack-mcp-server.
Related MCP Servers
n8n MCP Server
by n8n
Official instance-level MCP server that lets AI agents discover, run, and edit workflows on your n8n instance.
Airtable
by Domenic Rosati
Read and write Airtable bases from an AI client — records, schemas, fields, and views.
Taskade MCP Server
by Taskade
Open-source MCP server connecting agents to Taskade workspaces — projects, tasks, AI agents, and automations.
HubSpot
by HubSpot
HubSpot's official remote MCP server — read and write CRM contacts, companies, deals, and tickets through natural language.