MCP Servers · korotovsky

slack-mcp-server

slack-mcp-server is a Go-based Model Context Protocol server that enables AI assistants to read and post messages in Slack workspaces. It supports multiple deployment modes (OAuth or 'stealth' with no bot installation) and works with enterprise Slack setups, DMs, group conversations, and message search.

Talk to DEV.co Discuss Implementation

Source: GitHub — github.com/korotovsky/slack-mcp-server

1.7k

GitHub stars

336

Forks

Primary language

MIT

License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

Field	Value
Repository	korotovsky/slack-mcp-server
Owner	korotovsky
Primary language	Go
License	MIT — OSI-approved
Stars	1.7k
Forks	336
Open issues	45
Latest release	v1.3.0 (2026-05-14)
Last updated	2026-06-18
Source	https://github.com/korotovsky/slack-mcp-server

What slack-mcp-server is

A Go MCP server exposing Slack API operations (message history, threads, search, posting) via stdio/SSE/HTTP transports. Implements cursor-based pagination, date/count-based message limiting, user/channel caching, and optional message-posting guards via environment variables. Interoperates with Slack's conversations and search APIs.

Quickstart

Get the slack-mcp-server source

Clone the repository and explore it locally.

terminalbash

1git clone https://github.com/korotovsky/slack-mcp-server.git2cd slack-mcp-server3# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

AI-Assisted Slack Analytics & Reporting

Query historical messages, search conversations by date or content, and synthesize insights without LLM context limitations. Useful for meeting summaries, trend detection, or audit trails.

Agentic Slack Workflow Automation

Enable AI agents to autonomously read unread messages, post status updates, or thread replies in controlled channels (safeguarded by channel-ID allowlists). Reduces manual async communication overhead.

Enterprise & GovSlack Integration

Stealth-mode operation (no bot token refresh or permission scope escalation) suits restricted enterprise environments; explicit OAuth support for workspaces requiring token-based audit trails.

Implementation considerations

Deploy server as a standalone service (docker, systemd, serverless container) with network access to both the AI client and Slack's API endpoints; configure proxy settings if needed.
Authenticate via OAuth token (xoxp-* or xoxb-*) or stealth mode; stealth mode bypasses bot installation but behavior depends on Slack's client-side API restrictions.
Set SLACK_MCP_ADD_MESSAGE_TOOL environment variable to enable posting; use comma-separated channel IDs to restrict posting to specific channels for safety.
Implement caching for users and channels to reduce Slack API quota consumption; audit message history fetch limits (1d to 90d) relative to workspace history plan.
Test cursor-based pagination thoroughly; timestamp and count-based limiting may interact unexpectedly with timezone-aware filtering in date ranges.

When to avoid it — and what to weigh

Real-time Event Processing — Server fetches history and executes search queries on demand. Not designed for streaming event subscriptions or triggering on Slack events—use Slack's event API or bolt framework instead.
High-Volume Message Posting — Message posting is disabled by default and requires explicit environment variable configuration. Not optimized for bulk DM campaigns or transactional messaging at scale.
Slack App Marketplace Distribution — Server is self-hosted and workspace-scoped; cannot be packaged as a public Slack App. If you need to offer a managed SaaS product, this architecture is unsuitable.
Full Slack API Coverage — Implements only a subset of Slack APIs (conversations, search, basic posting). Features like user management, workspace settings, or file operations are not exposed.

License & commercial use

MIT License. Permissive OSI-approved license allowing commercial use, modification, and distribution with attribution.

MIT license permits commercial use without royalty or permission. However, verify that use of Slack API tokens and workspace data complies with Slack's terms of service and your workspace's data governance policies. Commercial deployments should include audit logging and explicit user consent.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

Signal	Assessment
Maintenance	Active
Documentation	Adequate
License clarity	Clear
Deployment complexity	Moderate
DEV.co fit	Good
Assessment confidence	High

Security considerations

Message posting is disabled by default (mitigation against accidental/malicious spam). Environment variable safeguards allow channel-level ACLs. No details provided on token storage, secrets management, or audit logging. Stealth mode's behavior relative to workspace access policies is not documented—verify compatibility with enterprise security policies. Transport encryption (TLS for HTTP/SSE) assumed but not explicitly confirmed.

Alternatives to consider

Slack Bolt Framework (Python/Node.js/Java)

Official Slack-maintained SDK for event subscriptions and app logic. Better for real-time event handling and marketplace app distribution; requires more code than MCP but offers full API access.

LangChain Slack Integration

Pre-built integration for LLM workflows. Lighter than a dedicated server but less flexible for transport selection and enterprise stealth-mode requirements.

Zapier / n8n Slack Connectors

No-code/low-code automation platforms with Slack support. Easier for business users but lack AI agentic reasoning and require separate subscription model.

Software development agency

Build on slack-mcp-server with DEV.co software developers

Deploy slack-mcp-server to connect your AI assistants with Slack workspaces. MIT-licensed, actively maintained, and ready for enterprise use.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

github-mcp-server mcp kubernetes-mcp-server

Related on DEV.co

Explore the category and the services that help you build with it.

MCP Servers AI Application Development Enterprise Software Integration API Development & Integration Talk to DEV.co

slack-mcp-server FAQ

What's the difference between OAuth and stealth mode?

OAuth mode uses explicit Slack tokens (xoxp-* or xoxb-*) and requires bot installation. Stealth mode relies on client-side API access without token refresh, useful for restricted enterprise networks but behavior depends on Slack's client restrictions.

Can I post messages to any channel?

No. Message posting is disabled by default. Enable via SLACK_MCP_ADD_MESSAGE_TOOL environment variable. You can optionally restrict posting to specific channel IDs via a comma-separated allowlist.

Does this work with bot tokens (xoxb-*)?

Partially. Posting and history fetching work with bot tokens, but the search.messages API is unavailable for bots; you must use a user token (xoxp-*) for search functionality.

What MCP clients are supported?

Any client supporting stdio, SSE, or HTTP transports (e.g., Claude Desktop, Cursor, Codeium, or custom implementations). Verify your client's MCP version compatibility.

Custom software development services

From first prototype to production, DEV.co delivers software development services around tools like slack-mcp-server. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across mcp servers and beyond.

Integrate Slack with Your AI Workflows

Deploy slack-mcp-server to connect your AI assistants with Slack workspaces. MIT-licensed, actively maintained, and ready for enterprise use.

Talk to DEV.co Schedule a Consultation