Slack MCP. Manage your entire team's comms without switching apps.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Slack MCP Server lets your AI agent interact directly with your workspace. You send messages, search historical chats across channels, list users, and add reactions—all without ever leaving your current workflow.
It's a direct API connection for automation.
What your AI agents can do
Channels history
Retrieves recent messages from a specific Slack channel in reverse chronological order.
Channels list
Lists all available public and private channels that the bot has access to within your workspace.
Messages search
Searches message content, usernames, and channels across the entire Slack workspace for keywords.
Lists all available public and private channels, and retrieves a directory of every user with their roles and status.
Finds specific messages by keyword, sender, or channel name anywhere in your entire Slack history. Results are sorted by most recent first.
Pulls back recent message threads and activity from any given channel ID for auditing or context gathering.
Posts new content to a specified channel, including sending private direct messages (DMs), optionally replying in an existing thread.
Adds an acknowledgment reaction to a message when you know the exact timestamp and location of that message.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Slack: 6 Tools for Communication Ops
These six tools let your AI agent read message logs, search chat history, list users, and post updates across any channel in your workspace.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Slack on Vinkius019d7609channels history
Retrieves recent messages from a specific Slack channel in reverse chronological order.
019d7609channels list
Lists all available public and private channels that the bot has access to within your workspace.
019d7609messages search
Searches message content, usernames, and channels across the entire Slack workspace for keywords.
019d7609messages send
Sends a new message to a specified Slack channel or sends a private direct message (DM).
019d7609reactions add
Adds an emoji reaction to a specific message after referencing the required channel ID and unique message timestamp.
019d7609users list
Lists all users in your Slack workspace, including their IDs, emails, names, and current status.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Slack, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Slack. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Sifting through chat history shouldn't feel like forensic accounting.
Right now, finding a specific decision from six weeks ago means logging into Slack, remembering which of the ten relevant channels to check, scrolling endlessly back through message threads, and then copying three lines of text just for your notes. It’s clicking between tabs, manual searching, and copy-pasting.
With this MCP server, you ask your agent directly: 'What was the final decision on feature X?' The agent runs `messages_search` across all relevant channels and gives you a concise answer, citing the exact message thread. You get the data without doing any clicks.
Messages Send MCP Server: Post updates instantly from chat.
Before this, posting an update to multiple teams required opening Slack, navigating to each channel manually, and hitting 'send' for every single one. If you missed a step, the whole rollout was inconsistent.
Now, your agent handles it all. You give the prompt—'Send the final deployment summary to #devs and @ops-leads.' It executes `messages_send` multiple times in sequence, keeping your workflow contained and accurate.
What you can do with this MCP connector
Man, this thing is clutch. Your AI client gets to act like it’s logged into your Slack workspace—it ain't just reading stuff, it’s actually doing things for you. You don't wanna switch tabs or copy and paste anything anymore; you just tell your agent what needs doing, and it handles the whole mess right inside the chat.
Discovering Your Workspace Layout
You can use channels_list to pull a full roster of every channel in the workspace—public ones, private groups, the works. It lists them all up so you know what's talkin' and where things live. When you need to know who’s on the team, users_list pulls that directory for ya. You get every user listed out with their IDs, email addresses, names, and even their current status.
That gives you a complete rundown of everyone working in the space.
Finding Specific Chats and Messages
Need to track down some old conversation? Forget scrolling forever. The messages_search tool lets your agent scan all the messages across the entire workspace. You can search by specific keywords, by the name of a user who said it, or even narrow it down by channel name. It finds that message anywhere in your history—and it sorts the results for you, most recent first so you ain't siftin' through crap.
If you need to focus on just one thread, channels_history retrieves a stream of recent messages from a single specified Slack channel. This pulls back activity in reverse chronological order, giving you a clean log of what was said lately for auditing or if you just wanna catch up quick.
Sending New Content and Replies
You don't gotta type out the updates yourself. You can use messages_send to post new content to any channel. It sends messages whether it’s a general update for the whole team or a private direct message (DM) with one specific person. Plus, you can have it reply directly within an existing thread, keeping all that context right where it belongs.
When someone says something important and you wanna acknowledge it without typing a full reply, reactions_add handles it. You just tell your agent which message you're talking about—you gotta give it the channel ID and the unique timestamp for that specific post—and it drops an emoji reaction right on top of it.
It’s instant acknowledgment.
It’s a direct API connection for automation, period. Your AI client is now part of your team’s workflow. You tell it to search, send, list users, or check history; it just does it.
019d7609-2d59-73c2-a477-b02fcff839d7 
How Slack MCP Works
- 1 Subscribe to this server and provide your Slack Bot Token.
- 2 Your AI client authenticates with the token, giving it access rights to your workspace data.
- 3 You give a natural language prompt (e.g., 'Search for API outage mentions last week'), and the agent runs the necessary tools against the live Slack environment.
The bottom line is, you manage your entire team's communication flow directly from your chat window using only prompts.
Who Is Slack MCP For?
Anyone who spends too much time switching between their messaging platform and other dashboards. This is for the Ops Engineer tired of checking ten different channels for a status update, the Team Lead needing to audit past decisions quickly, or the Developer who needs to post deployment notes without leaving their IDE.
Audits communication patterns across multiple channels and coordinates responses by running searches or listing users.
Posts deployment updates to specific engineering channels, and runs targeted searches for error reports or past architectural decisions.
Uses the tool to list users and browse channel structures, gathering context needed to write documentation or summarize project status.
What Changes When You Connect
- Stop digging through threads for old info. Use
messages_searchto find any keyword, user, or channel across years of chat history instantly. - Need a status report? Run
users_listto pull names, roles, and emails, letting you build out documentation without logging into the directory manually. - Running low on context? Use
channels_historyto grab the last 50 messages from an #incidents channel. You get immediate situational awareness. - Finished a project task? Use
messages_sendto broadcast a final 'done' status update to your core team channel, keeping everyone in the loop. - Missed an important chat decision? Run
channels_listfirst to map out all channels, then usechannels_historyon the right one. It’s faster than asking a colleague. - Acknowledging messages becomes part of the workflow. Use
reactions_addfor quick confirmation without needing to type anything.
Real-World Use Cases
Incident Review and Root Cause Analysis
A developer is investigating a production outage. They ask their agent to run messages_search for 'database connection' from the last 7 days across all #dev channels. The agent returns eight relevant messages, pinpointing when the issue first appeared and who was involved.
Onboarding New Team Members
The manager needs a list of everyone on the new marketing team. They prompt the agent to run users_list. The agent returns names, email addresses, roles, and current statuses, allowing the manager to build welcome emails immediately.
Project Status Update Broadcast
The project lead finishes a milestone. Instead of manually posting in three different channels, they prompt the agent to run messages_send with the update message, hitting #general and #product-roadmap simultaneously.
Catching Up After Vacation
You've been out for a week. You ask your agent to review #sales-leads history using channels_history. The agent pulls the last 100 messages, letting you understand key decisions and context without reading hundreds of individual threads.
The Tradeoffs
Searching by vague topic
Asking for 'all talks about Q3' is too broad. The agent might return thousands of results, forcing you to wade through irrelevant chats.
→
Always narrow the scope. Use messages_search with specific names or dates: 'Search for John Doe and Q3 in #product-roadmap from last month.' Specify who and when.
Trying to manage files
Thinking this server can find a spreadsheet shared by someone three months ago. It only handles message text, not file attachments.
→
Use messages_search for keywords within the chat history. If you need external data (like a database record), use a dedicated data source tool.
Assuming channel access
Asking to read history from #executive-meetings when your bot token doesn't have permission for that specific private channel.
→
First, run channels_list. This confirms which channels are visible and accessible before you try to read their history using channels_history.
When It Fits, When It Doesn't
Use this server if your primary pain point is managing communication context. You need to automate sending messages, retrieving chat logs, or finding out who's in the office right now. The core functionality revolves around reading and writing text-based conversations.
Don't use it if you need to interact with structured data outside of Slack (like updating a CRM record, manipulating calendar invites, or running complex financial calculations). For those tasks, you'll need tools that connect to dedicated databases or APIs. This server is purely for messaging workflow automation.
Common Questions About Slack MCP
How do I get started with Slack MCP? +
Subscribe, then create a Slack App at api.slack.com/apps → Create New App. Go to OAuth & Permissions, add the required bot scopes (channels:read, chat:write, search:read, users:read), install the app to your workspace, and paste the Bot User OAuth Token (starts with xoxb-) here. No code, no webhooks — just connect and go.
Can my AI agent send messages and reply in threads? +
Yes. Your agent can post to any channel the bot has been invited to — including threaded replies. Just say 'post in #engineering that the deploy is complete' or 'reply in the thread about the bug fix'. It supports Slack's full mrkdwn formatting including bold, links, code blocks, and mentions.
How can I find a specific conversation from last week? +
Tell your agent to search for it — 'find messages about the Q3 budget review' or 'search for messages from @sarah about the client proposal'. The agent uses Slack's search API with support for modifiers like from:user, in:channel, and date ranges. No more scrolling through channels — your agent retrieves the exact messages you need.
Can I manage multiple channels and monitor team activity? +
Absolutely. List all channels to get an overview of your workspace structure, read history from specific channels to audit conversations, and check team member profiles, statuses, and timezones. Perfect for distributed teams, engineering organizations, and operations managers who need a bird's-eye view of communication across dozens of channels.
How does using the `channels_list` tool help me understand my workspace structure in Slack? +
It returns a comprehensive list of all public and private channels your bot can see. This process gives you the necessary Channel IDs, which are required to send messages or read history later.
Using `users_list`, how do I retrieve information about team members in Slack? +
The tool provides user IDs, names, emails, and current statuses. This lets your agent accurately identify message authors or send targeted direct messages without manual searching.
If I need to audit activity, how does the `channels_history` tool retrieve past messages from Slack? +
It fetches recent messages in reverse chronological order. You must provide a Channel ID first; this mechanism is key for auditing or reviewing threads within specific channels.
How do I use the `reactions_add` tool to quickly acknowledge a message in Slack? +
You can add an emoji reaction to any specific message. Be sure you have both the Channel ID and the exact message timestamp (ts)—the history tool helps get that time.
Multi-server workflows that include Slack MCP
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.