Back to MCP Servers

Slack

Your complete Slack context for Claude—DMs, channels, threads, search. No OAuth apps, no admin approval. `--setup` and done, 11 tools, auto-refresh.

communicationslack
By jtalk22
2917Updated 6 days agoJavaScriptMIT

Installation

npx -y slack-mcp-server

Configuration

{
  "mcpServers": {
    "slack-mcp-server": {
      "command": "npx",
      "args": ["-y", "slack-mcp-server"]
    }
  }
}

How to use

  1. Run the installation command above (if needed)
  2. Open your Claude Code settings file (~/.claude/settings.json)
  3. Add the configuration to the mcpServers section
  4. Restart Claude Code to apply changes

Slack MCP Server

npm version MCP Registry License: MIT

Give your AI agent full Slack access — and structured workflow output the AI can actually use. No app registration, no admin approval, no OAuth. One command, 21 tools, works with any MCP client.

npx -y @jtalk22/slack-mcp --setup

Slack MCP Server Demo

▶ Watch the demo — 7 scenarios, from 47 unreads to inbox zero, without opening Slack.

Ask your AI to catch you up on #engineering from the last 24 hours. Search for that deployment thread from last week. Find the printer admin PIN nobody can remember. Send a reply. All from your editor.

Interactive demo · Latest release

Why This Exists

Slack's official MCP server is OAuth-first and can require a registered app, admin approval, or client compatibility workarounds. See the tracked Claude Code/GitHub Copilot compatibility discussion. Screenshotting messages is not a workflow.

This server uses your browser's session tokens instead. If you can see it in Slack, your AI agent can see it too. No app install, no scopes, no admin.

Session-token transport: No bot user appears in the workspace admin panel, no app install shows up, no audit trail entry is created. Your AI agent operates with the same workspace footprint as your browser tab — nothing more, nothing less.

OAuth vs Chrome DB Decryption

Slack Official MCPThis Server
OAuth app requiredYesNo
Admin approvalYesNo
Works with Claude CodeNo (DCR incompatible)Yes
Works with CursorNoYes
Works with CopilotNoYes
Works with WindsurfNoYes
Works with Gemini CLINoYes
Works with Codex CLINoYes
Setup time~30 min~2 min
ToolsLimited21
Visible to adminsYesNo — session-token transport

Workflow Primitives

Introduced in 4.2. Save a workflow profile that binds a workflow_kind to channels + priority people + retention + cadence. Stored locally at ~/.slack-mcp-workflows.json. The hosted brain at mcp.revasserlabs.com reads these profiles and returns structured JSON per workflow_kind — downstream automation (Linear, Notion, status dashboards) consumes the JSON directly.

workflow_kindReturns (structured JSON)
incident_room{incident_summary, timeline, open_risks, owner_gaps, next_actions}
exec_brief{summary, decisions, risks, asks, action_items}
support_inbox{open_threads, ack_lag, owner_gaps, escalations, next_actions}
product_launch_watch{launch_signals, feedback_themes, blockers, metrics, next_actions}
custom{summary, highlights, open_questions, next_actions}

Six prebuilt templates ship with the package:

npx -y @jtalk22/slack-mcp --apply-template oncall-handoff --channels C012345,C067890

Available templates: oncall-handoff, support-triage, exec-monday, sprint-tracker, customer-feedback, incident-room. The structural primitives (slack_workflow_save, slack_workflows) are free forever in OSS; the hosted brain is $0 to start (no card) and $19/mo Pro for unlimited AI tools.

Quick Start per Client

<details> <summary><strong>Claude Desktop / Claude Code</strong></summary>

Add to ~/.claude.json or Claude Desktop settings:

{
  "mcpServers": {
    "slack": { "command": "npx", "args": ["-y", "@jtalk22/slack-mcp"] }
  }
}
</details> <details> <summary><strong>Cursor</strong></summary>

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "slack": { "command": "npx", "args": ["-y", "@jtalk22/slack-mcp"] }
  }
}
</details> <details> <summary><strong>Windsurf</strong></summary>

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "slack": { "command": "npx", "args": ["-y", "@jtalk22/slack-mcp"] }
  }
}
</details> <details> <summary><strong>Gemini CLI</strong></summary>

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "slack": { "command": "npx", "args": ["-y", "@jtalk22/slack-mcp"] }
  }
}
</details> <details> <summary><strong>Codex CLI</strong></summary>

Add to ~/.codex/config.toml:

[mcp_servers.slack]
command = "npx"
args = ["-y", "@jtalk22/slack-mcp"]

Or via CLI: codex mcp add slack -- npx -y @jtalk22/slack-mcp

</details>

Tools

ToolDescriptionSafety
slack_health_checkVerify token validity and workspace inforead-only
slack_token_statusToken age, health, and cache statsread-only
slack_refresh_tokensAuto-extract fresh tokens from Chromeread-only*
slack_list_conversationsList DMs and channelsread-only
slack_conversations_historyGet messages from a channel or DMread-only
slack_get_full_conversationExport full history with threadsread-only
slack_search_messagesSearch across workspaceread-only
slack_get_threadGet thread repliesread-only
slack_users_infoGet user detailsread-only
slack_list_usersList workspace users (paginated, 500+)read-only
slack_users_searchSearch users by name, display name, or emailread-only
slack_conversations_unreadsGet channels/DMs with unread messagesread-only
slack_send_messageSend a message to any conversationdestructive
slack_add_reactionAdd an emoji reaction to a messagedestructive
slack_remove_reactionRemove an emoji reaction from a messagedestructive
slack_conversations_markMark a conversation as readdestructive
slack_workflow_saveSave a workflow profile (channels, kind, retention, cadence) to ~/.slack-mcp-workflows.jsonlocal-write
slack_workflowsList saved workflow profilesread-only
slack_smart_searchSemantic search across indexed channels — hosted brainhosted-stub†
slack_catch_me_upAI-summarized digest of unreads + priority threads — hosted brainhosted-stub†
slack_triagePrioritized action queue across channels — hosted brainhosted-stub†

21 tools total: 12 read-only Slack, 4 write-path Slack, 2 workflow profile primitives (1 local-write, 1 read-only), 3 hosted stubs. All carry MCP safety annotations.

* slack_refresh_tokens modifies local token file only.

† Hosted stubs return a structured upgrade payload (signup_url, free_tier_quota, pro_value_prop) — no Slack write occurs from OSS. Activate the brain at mcp.revasserlabs.com (free tier, no card).

‡ Also accepts include_rich_message_fields to return attachments, blocks, files, reactions, and metadata — see Rich Message Fields.

Install

Node.js 20+

npx -y @jtalk22/slack-mcp --setup

The setup wizard handles token extraction and validation.

After setup, have your client run slack_health_check — a workspace name in the response confirms you are connected.

<details> <summary><strong>Claude Desktop (macOS)</strong></summary>

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "@jtalk22/slack-mcp"]
    }
  }
}
</details> <details> <summary><strong>Claude Desktop (Windows/Linux)</strong></summary>

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "slack": {
      "command": "npx",
      "args": ["-y", "@jtalk22/slack-mcp"],
      "env": {
        "SLACK_TOKEN": "xoxc-your-token",
        "SLACK_COOKIE": "xoxd-your-cookie"
      }
    }
  }
}

Windows/Linux users must provide tokens via env since auto-refresh is macOS-only.

</details> <details> <summary><strong>Claude Code</strong></summary>

Add to ~/.claude.json:

{
  "mcpServers": {
    "slack": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@jtalk22/slack-mcp"]
    }
  }
}

Or via CLI: claude mcp add slack -- npx -y @jtalk22/slack-mcp

</details> <details> <summary><strong>Cursor / Copilot / Other MCP clients</strong></summary>

Any client that supports stdio MCP servers works. Add to your client's MCP config:

{
  "slack": {
    "command": "npx",
    "args": ["-y", "@jtalk22/slack-mcp"],
    "env": {
      "SLACK_TOKEN": "xoxc-your-token",
      "SLACK_COOKIE": "xoxd-your-cookie"
    }
  }
}

On macOS, tokens are auto-extracted from Chrome — env block is optional.

</details> <details> <summary><strong>Claude Web / Remote MCP</strong></summary>

Hosted tiers at mcp.revasserlabs.com:

TierPriceWhat it owns
Self-hostFree (MIT)Local stdio, all 21 tools (16 read/write Slack + 2 workflow profile primitives + 3 discoverable upgrade stubs to hosted brain)
Hosted Free$0 (no card)Email signup, 1 workspace, 2,000 requests/mo + 25 AI tool calls/mo. All 5 workflow profile types. 7-day index retention.
Pro$19/mo or $190/yrUnlimited requests (fair use), unlimited AI tool calls, permanent OAuth, email support, 2 workspaces
Team$49/mo or $490/yr flatEverything in Pro + shared workflow profiles, 5 workspaces, 24h support
Safeguard$199/mo — waitlistAgent approval gates, scheduled catch-up DM, workspace memory — all (in development). Waitlist only.
</details> <details> <summary><strong>Docker</strong></summary>
docker pull ghcr.io/jtalk22/slack-mcp-server:latest
{
  "mcpServers": {
    "slack": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
               "-v", "~/.slack-mcp-tokens.json:/root/.slack-mcp-tokens.json",
               "ghcr.io/jtalk22/slack-mcp-server"]
    }
  }
}
</details>

Restart your client after configuration. Full setup: docs/SETUP.md

How It Works

Session tokens (xoxc- + xoxd-) from your browser. If you can see it in Slack, this server can see it too.

Token persistence — four-layer fallback:

  1. Environment variables (SLACK_TOKEN, SLACK_COOKIE)
  2. Token file (~/.slack-mcp-tokens.json, chmod 600)
  3. macOS Keychain (encrypted)
  4. Chrome auto-extraction (macOS)

Tokens expire. The server notices before you do — proactive health monitoring, automatic refresh on macOS, warnings when tokens age out. File writes are atomic (temp file → chmod → rename) to prevent corruption. Concurrent refresh attempts are mutex-locked.

<details> <summary><strong>What's New in 4.2.0</strong></summary>
  • Workflow primitivesslack_workflow_save + slack_workflows bind a workflow_kind (incident_room, exec_brief, support_inbox, product_launch_watch, custom) to channels, priority people, retention, and cadence. The hosted brain returns structured JSON per kind — incident_room returns {incident_summary, timeline, open_risks, owner_gaps, next_actions}, exec_brief returns {summary, decisions, risks, asks, action_items}. Downstream automation (Linear, Notion, dashboards) consumes the JSON directly.
  • Discoverable upgrade stubsslack_smart_search, `sla

View source on GitHub