# Slack — MCP Server

> Search workspace, read threads, post updates and work with Slack from chat.

**Source:** https://mcpplaygroundonline.com/mcp-servers/slack  
**Transport:** http  
**Requires auth:** Yes

---

## What it does

The Slack MCP server is built for LLM use: you get tools for content search (messages, files, channels, people), reading a channel or thread history, sending or drafting messages, creating or updating Slack canvases, and reading user profiles. Workspace admins can approve the calling app, and the same product rate limits apply as the Web API. For Agent Studio, configure the pre-filled URL, install your app to the workspace, and pass the token your client documents — typically a bot `xoxb-` token with chat, search, and history scopes.

## Tools exposed

- Search messages and files — query workspace content with filters (see Slack’s MCP rate table)
- Search users / Search channels — resolve people and channels by name or ID
- Send message / Draft message — post or stage messages to a conversation
- Read a channel / Read a thread — fetch history for a channel or reply chain
- Create or update a canvas / Read a canvas — collaborative docs inside Slack
- Read a user profile — members, custom fields, and status when scopes allow

## Example queries you can run

- "What did I miss in #engineering since yesterday? Summarise the main threads."
- "Search for every message mentioning "SLO" in the last 14 days and group by channel."
- "Who is in the #releases channel and when was the last post?"
- "Draft a short standup I can post to #standup based on my recent thread activity."

## Details

- **Recommended model:** anthropic/claude-sonnet-4.5 — Claude Sonnet 4.5 is stronger on long thread synthesis and safe messaging. The Slack template uses Haiku 4.5 for lighter search; compare in Agent Studio.
- **Transport:** http
- **Authentication:** Required — Slack app installed to the workspace. Use the bot user OAuth token (`xoxb-…`) and scopes for search, history, and chat:write (see Slack MCP docs for the full set).
- **Hosted endpoint:** https://mcp.slack.com/mcp
- **Official source:** [Slack MCP server docs](https://docs.slack.dev/ai/mcp-server)

## Frequently asked questions

### What is the Slack MCP server?

It is Slack’s hosted Model Context Protocol service at mcp.slack.com/mcp. It exposes your workspace in tools so an AI can search, read conversations, post messages, and work with canvases, subject to app approval, scopes, and the same rate limits as Slack’s APIs.

### What token and scopes do I need?

Create a Slack app, install it to your workspace, and grant the scopes the MCP tools require: typically search, channel history, and chat:write for posting. Copy the bot user OAuth token and supply it in your MCP client. Admins may need to approve the app for the workspace.

### Can the agent post or delete messages everywhere?

The app only sees channels and DMs the token can access. Start with a narrow set of test channels, avoid broad chat:write until you are comfortable, and review messages the model proposes before they go out if your client does not require approval for every post.

### Does the Slack MCP server work with Claude, ChatGPT, Cursor, and MCP Agent Studio?

Slack partners with several clients, and any MCP client that can send streamable HTTP to the endpoint with a valid token can work. In this project, use MCP Agent Studio: choose the Slack template or paste mcp.slack.com/mcp and your token.

### Which model is best for Slack search and catch-up summaries?

Claude Sonnet 4.5 handles long thread synthesis and disambiguation well. For cheap high-volume search-only tasks, try Claude Haiku 4.5. Compare them side by side in Agent Studio on a real catch-up question.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/slack — free, no install._