Slack Release Notes

• Set up and configure the Tableau Next MCP server to give Slackbot access to your Tableau data.

• On Enterprise plans, Channel Managers can prevent members of their organization from updating the topic or description for channels they manage.

• When you mention an AI agent (like @claude or @codex) in a direct message, you can convert it to a new private channel that includes all current members and message history.

• Messages with multiple images or videos now display all media in a single row, so no more endlessly tall messages.

• Past conversations in your Slackbot History tab now have names so they’re easier to tell apart. Click on a conversation’s name to view it, or click Rename to re-label it.

• We’ve simplified Slackbot task limits to three automatic runs per day. Once you reach the daily limit (which resets at midnight in your time zone), Slackbot will ask if you’d like to run tasks manually.

Slack is where work happens. Slackbot is how it happens, giving everyone an AI teammate to help them get more done.

Hi, I’m Slackbot 👋

Most AI agents only know what you tell them. I already know how your business works — the conversations, decisions, and data built up over years. And I don't just answer questions, I work with every app and agent connected to Slack.

Watch video The new AI-powered Slackbot can tell you your daily priorities, draft documents, summarize conversations, analyze files, and much more. Get to know your personal AI agent for work, right within Slack.

Ask me anything. I’ll take care of the rest.

Find answers with Slackbot. Ask in your own words and Slackbot will find what you need across messages, channels, files, and connected apps.

I work across all your apps so you don’t have to

While you’re hard at work in Slack, I’ll work alongside your apps and agents. Ask about pipeline risk, a product launch, or an IT issue, and I’ll find who and what you need to solve the problem. Soon I’ll be able to work across Agentforce, Tableau, MuleSoft, and Salesforce data, too. No tool-switching. No re-explaining yourself.

Watch video A video showing examples of how Slackbot is the ultimate AI teammate.

I’m your personalized AI, right where you work

Manage customers with Slack CRM

I help small businesses manage customers with ease. Ask me to create accounts, update records, prep for meetings, log calls and notes, generate summaries, or draft follow-ups. Managing your accounts is as easy as messaging a teammate.

Consider all your work secured

What’s shared with me stays with you. I only surface what you have access to, your interactions are private, and your data is never used to train AI. Slack’s security and compliance standards apply to every request.

CUSTOMER SPOTLIGHT

Slackbot helps MrBeast create viral videos

Watch me work 👀

Watch video See how MrBeast uses Slackbot

Don’t just take my word for it

The world’s most innovative companies use Slackbot

"Our teams use Slackbot for everything from quick analytics to creating canvases. Using the summary feature alone likely saves 15 to 20 minutes per use, preventing dropped balls."

• Mollie Bodensteiner, SVP of Ops, Engine

"At Beast Industries, we turn improbable ideas into reality, and that means we have to create at light speed, at scale, on brand. Slackbot allows our teams to save time on operational tasks so they can focus on creating amazing experiences for MrBeast fans worldwide. Whether we’re coordinating a 1,000-person production or building schools in Ghana, Slackbot quickly turns scattered data into a clear plan of action, allowing us to hit our deadlines and stay on budget without having to slow down."

• Luis Madrigal, CIO, Beast Industries

"Instead of switching between multiple applications and windows and losing my train of thought, I can ask Slackbot questions, have it conduct research and create content without ever leaving Slack/the place I am working all day. It's transformed how efficiently I move through my day—no context switching, no friction."

• Christine McHone, Global Enterprise TMT Leader, Slalom

"Because so much of our work happens in Slack, Slackbot already understands our world. I don’t have to write a long brief to get it up to speed on what we’ve been working on or how the team operates; it just gets the context from day one."

• Megan Harrigan, Director of Global CX Projects & Readiness at Xero

Frequently asked questions

How is Slackbot different from other AI tools?

Slackbot isn’t just another standalone agent — it works where your teams already collaborate. Because it lives directly inside Slack, it can use your organization’s shared history, files, and conversations to provide relevant, high-quality answers without switching apps or losing context. Slackbot brings AI into the natural flow of work so teams can get value instantly.

What can Slackbot help me with?

How does Slackbot protect the security of our data?

Does Slackbot work globally?

How does Slackbot help with customer relationship management?

What are the most common use cases for Slackbot?

Which plan do I need to use Slackbot?

See all you can accomplish in Slack.

ENTERPRISE SEARCH

Search everything. Find anything.

Say hello to enterprise search, where all your conversations, data, and third-party apps are searchable from a single, AI-powered search bar.

Search Slack, and every connected app.

Enterprise search includes your company's third-party apps, too. No context switching required.

FULLY CONNECTED

One search to rule them all.

With enterprise search, Slack is the gateway to your company’s collective knowledge. Search across all your conversations, business tools, and data — all from a single search bar in Slack.

AI-POWERED

Search it the way you say it.

No more piecing data together from multiple sources. Just ask a question, and enterprise search will pull from all of your business apps to bring you the answer you need, right there in Slack.

CUSTOM SOURCES

Make high-value data sources more accessible.

Plug knowledge gaps using an API to bring your most valuable sources to enterprise search.

Securely connect your home-grown systems, self-hosted software, and proprietary knowledge bases, with enterprise-grade security intact.

SECURITY FOCUSED

Permission-aware results, personalized for you.

Slack searches employ strict guardrails, and customer data never leaves Slack’s trust boundary. AI works to better understand your tasks, goals, and projects, so you get personalized results without compromising security.

"We need a single pane of glass for all our data sources across our different systems. Enterprise search in Slack delivers exactly that. With the help of AI, we can surface all the right information directly in front of our users."
HC Madsen
Senior IT Systems Engineer, EasyPark Group

"Enterprise search has now become a go-to-place for me to learn about our business. I ask conversational questions, and Slack creates useful context in addition to providing credible responses to the questions I have."
Paul Kagoo
GM of Enterprises and B2B, reMarkable

REIMAGINE SEARCH WITH SLACKBOT

Meet Slackbot: Your new personal AI agent for work.

Slackbot is here as your all-new personal search agent! Beyond simply surfacing conversations, Slackbot can analyze information to deliver contextual insights from all of your permissioned conversations, files, and projects. Slackbot finds exactly what you need — all you have to do is ask.

Customer management, made conversational

With Slack CRM, managing customers is as easy as asking Slackbot. Your personal AI agent can capture contacts, track deal progress, and prep what you need with a simple prompt – right in Slack.

WORK SMARTER

Take the work out of work with Slackbot. Research accounts, prep meetings, and draft follow-ups in seconds. With a simple ask, Slackbot tackles the busywork and keeps data up to date, so your team can spend more time building relationships.

"Before, I was spending hours every week juggling spreadsheets. Now I just tell Slackbot what happened after a call, and it updates everything automatically. I'm saving at least 90 minutes a day on admin work—time I can actually spend with customers."

Sia Ghazvinian, Co-founder and CEO

STAY ORGANIZED

Turn conversations into customer records. Slackbot knows your channels, conversations, and customers, and can take instant action based on your prompts. Spin up a new account, log notes from a recent call, and update your records, all in Slack — all you have to do is ask.

"Having everything in one place is a game-changer — from prepping to navigating my day with the agenda view and Slackbot's suggested focus areas, I never have to leave Slack."

Em Smith, Founder

SET UP IN SECONDS

Start simple, then grow when you’re ready. Start with what you need today, right inside Slack. Every conversation, customer, and update connects to Salesforce in the background. When your team is ready for a full CRM, nothing needs to be migrated — everything you’ve captured in Slack is already there.

"When we launched, we couldn’t justify expensive CRM software. Slack CRM gives small teams what they need right where they work—no switching tabs, no learning another platform."

George Graham, Founder and CEO

Whatever you need, just ask Slackbot.

• Track Your Pipeline

Manage sales with a dynamic kanban board. Ask Slackbot to create a lead or update a record and it’ll appear in your Sales Tracker.

• Prep for Meetings

Prep is no sweat when Slackbot can generate a brief with deal status, recent activity, and key talking points.

• Update Deals

Move a deal forward or log what happened in seconds. Slackbot keeps everything current as you work.

• Speed Up Outreach and Support

Ask Slackbot to route requests and draft responses to get customers answers fast. Plus, send personalized emails to customers at any stage.

Get to know AI in Slack

"At first, it felt like a small workflow improvement. But over time, we saw the compounding effect. Better conversations led to better pipeline, which led to better conversions."

Gerardo Rodriguez Phillip

Co-founder & CEO

Sparked

Frequently Asked Questions

Why do small businesses need a CRM?

As your business grows, customer information can become scattered across emails, spreadsheets, and multiple different apps. Or, worse, all those details are stuck in one person’s head. A CRM helps centralize contacts, track deals, and manage follow-ups so nothing gets missed. Even small teams benefit from having one place to organize customer relationships.

Summer has a way of clarifying what actually matters. You want to spend time out in the sun, not wasting time bouncing between apps to get your work done.

This June, we shipped across every layer of Slack. Slackbot learned to remember you, reach your whole tool stack, speak your language, and turn your data into something you can actually see. Direct messages and the sidebar got easier to navigate. And the platform opened up so the apps your team already relies on can show up right inside your conversations — not just as notifications, but as places where work gets done.

The throughline? Less switching. Less searching. Less explaining yourself from scratch every morning.

Here’s everything that landed this month.

Slack connects your whole stack

The context-switching problem just got a lot smaller. This month, Slack becomes the place where your tools actually talk to each other — not just notify you.

Slackbot MCP Client uses the Model Context Protocol to connect your AI assistant to the tools your team already runs on — Google, Atlassian, Box, Notion, DocuSign, and more. One conversation can now pull from your entire stack. You don’t have to leave Slack to get the answer. Slackbot reaches where the work is.

And it’s not just Slackbot reaching out. With Partner MCP Apps, the tools your team loves can now reach into Slack. Box, Figma, DocuSign, Linear — instead of firing off a notification and walking away, these apps can surface live data, interactive forms, dashboards, and action panels right in your conversation. Sign a document. Update a ticket. Pull a design. Without leaving Slack once.

Slackbot learns you, and gets out of your way

AI assistants have a short-term memory problem. You explain your role, your team, your preferences, yet in the next conversation, you start over. Not anymore.

Slackbot Memory means Slackbot actually learns your work — not just what you told it, but what actually happened. The channels you’re in, the decisions your team made, the projects that shaped your context. Week one it knows your name. Week eight it knows your stakeholders, your tone, and what “urgent” means to you. The longer you use it, the more useful it gets. No manual training required.

And Slackbot keeps getting easier to use, however you work:

• Voice Actions — For anyone who never opened Slackbot because typing felt like one more thing, you can now just say it out loud.
• Native Charts — Slackbot can now turn your raw data into visual charts right in the conversation. No pivot tables. No third-party tools. Ask a question, get an insight — right where decisions get made.

A better workspace for everyone

The Slackbot upgrades get a lot of attention, but this month’s drop also improves the fundamentals — the surfaces everyone uses every day.

Named group DMs are (finally!) here. Group DMs have been nameless since they launched in 2015. Eleven years of “you, Sarah, Mike, and 3 others.” Now you hover, click the pencil, and give it a name or an emoji. No more sending the wrong message to the wrong people.

Sidebar filtering makes it easy to find what you need without the scroll. All you have to do is type to filter your sidebar in real time. Fuzzy matching, recency sorting, group DM-aware — it works across the Home and DMs tabs, with a handoff to Search when there are no results.

Ready to put it all to work?

Check out our Innovations webpage for previous releases.

Please note that some features may not be immediately available in your workspace depending on the rollout timeline, your Slack licensing plan, or additional license requirements. To learn more about feature availability, check with your admin on the licensing plans for your workspace.

Ready to learn more? Contact us.

How three months changed what Slackbot can do for every employee

TABLE OF CONTENTS

April: Slackbot learned to act

May: Slackbot learned to see

June 24: Slackbot learns you. Your team. Your stack. And it listens.

Key takeaways

• Slackbot gets smarter the more you use it.
  Memory means you spend less time re-explaining your context. It learns how you and your team work and builds on it with every conversation.
• Your whole stack, one conversation:
  Slackbot MCP connects Google, Atlassian, Box, Notion, DocuSign, and more so you can act across tools without switching apps.
• Just say it:
  Voice Actions let you speak naturally and Slackbot acts on what you mean, not just what you said.
• From data to visual in seconds:
  Native Charts turn raw data into clear visuals without leaving Slack.

Every few months, something shifts. What you’re doing in Slack today wasn’t possible three months ago.

In April, Slackbot learned to act. In May, it learned to see. On June 24, it learns you, your team, and your entire stack. And it listens.

This is the story of those three months. And why the last chapter changes what the first two made possible.

April: Slackbot learned to act

The team built it because asking Slackbot to help and then doing the work yourself isn’t help. In April, that changed. Slackbot could now take action: create records in Salesforce, run tasks on a schedule, build skills that did the work inside the systems your team already runs on.

An AI that answers questions is useful. But answering a question about a deal versus actually updating the deal record, logging the activity, and flagging the follow-up, are two very different things. One saves you a few seconds of searching. The other improves your output and moves your work forward.

Raveesh Raina, a sales engineer at Salesforce, built a skill to log his activity after customer calls. He shared the skill and within three weeks, 466 of his colleagues were using it. 73% found it through word of mouth. Forty-three minutes saved, per person, per week.

That’s what it looks like when one person’s best process becomes everyone’s capability.

May: Slackbot learned to see

The team built it because the best answer in the world doesn’t help if it lives in someone else’s browser history. In April, Slackbot could act. In May, it could see.

In May, Slackbot could reach outside Slack and bring what it found back into the conversation. Search the web, read a PDF, build a Native Chart from raw numbers, or highlight any text and ask Slackbot to explain it in context. The output didn’t disappear into a separate tool or a file no one would open. It landed right where the work was already happening, ready for the whole team to see and build on.

This is the part that matters for everyone else on the team. The person who did the work didn’t have to translate it into a separate deliverable. The conversation was the deliverable.

June 24: Slackbot learns you. Your team. Your stack. And it listens.

You’re walking out of a meeting. An idea lands. You don’t have a free hand.

That’s when you need Slackbot. Voice Actions make that possible. Open Slackbot on your phone and say what needs to happen: log the call, update the record, capture the thought before it disappears. Slackbot already knows your context, so you don’t have to re-explain. You just say it out loud.

That works because Slackbot already knows you. And the longer you use it, the more it knows.

And it doesn’t wait to be asked. Slackbot can act on a schedule, fire when a message lands in a channel, kick off when someone adds a reaction. That’s a different kind of AI than one that shows up when you tag it.

The AI that knows your team, not just you.

April and May were about capability. June goes deeper on something that’s harder to build: context.

The team built it because we want AI that knows our work. April and May were about capability.

Most AI has memory now. But there’s a difference between an AI that remembers what you told it and one that knows what your organization knows. Some AI reads the room when you ask it to. Slackbot has been in the room all along. Every other AI learns what you told it: your role, your preferences, the context you typed into a settings panel. Slackbot learns what your team actually did. The decision made in a channel last month. The project thread where the real answer lives. The Salesforce deal context from the call that happened in Slack. You didn’t have to brief it. It was already there.

The more you work in Slack, the sharper it gets. Ask it to draft a follow-up on a deal you haven’t touched in six weeks and it already knows the stakeholders, the sticking points, and the last thing your champion said. Not because you told it. Because that’s where the work happened. That context compounds.

It doesn’t stop with you.

Memory makes Slackbot better the more you use it. Skills spread that to your team.

Think about the last time a colleague figured something out that would have saved you an hour, and you never knew. The perfect way to prep for a renewal call. A prompt that turns a messy data pull into something a VP can read in 30 seconds. That kind of knowledge used to travel by word of mouth, if it traveled at all. With Slackbot there’s a way to share and build on what your colleagues have already figured out. When someone on your team builds a skill, everyone benefits.

Your whole stack, one conversation.

Context is only useful if it can follow you. With MCP, it does. Most teams run on five or more apps. With MCP, Slackbot brings your whole stack into the conversation — Google, Atlassian, Box, Notion, DocuSign, and more. You don’t have to leave to get the answer. You don’t have to re-explain the context. Slackbot reaches where the work is and brings it back to where the conversation is already happening.

That’s the through-line across all of this. Memory makes Slackbot better for you. Skills spread that to your team. MCP brings the rest of your stack into the conversation. Every employee gets an AI that gets smarter not just because they used it, but because everyone around them did too.

And, for the employee who never opened Slackbot because typing felt like one more thing, you can now just say it out loud.

Open Slackbot. Ask it: “What do you know about me?”

That’s where it starts. And it gets better from there.

Now you can work with over 20 partner applications that integrate with Slackbot and shared channels

By the team at Slack
June 17th, 2026

Think about the five apps you can’t do your job without. Now count how many of them talk to each other. If you’re in sales, your deals live in one tool, your contracts in another, your decks in a third. If you’re an engineer, your tickets, your incidents, and your code reviews are three different tabs. Every one of those apps got an AI assistant this year. None of them got any closer together. While organizations keep paying for an increasingly fragmented stack, teams are left manually carrying data between isolated systems.

The real cost isn’t just lost hours or fractured software ROI. It’s that all of this stitching happens alone, in private tabs, where critical answers end up languishing in isolated histories. Your teammates are doing the exact same dance with the same apps, with no way to scale best practices or build on each other’s momentum.

Today, we’re changing that. Slackbot’s Model Context Protocol (MCP) client is now generally available. Built on the open MCP standard that’s been adopted across the industry, it connects any app to Slackbot, whether that’s a Salesforce product, a third-party tool, or something your own team built. This allows businesses to finally maximize their existing software investments by unifying their disconnected systems. Instead of juggling a dozen isolated AI tools across a dozen browser tabs, you get a single conversational interface where everything works together. Just ask Slackbot in plain language, and it will instantly pinpoint the right tool and coordinate the exact steps to finish the task.

To bring this to life, we’re launching a partner ecosystem of more than 20 MCP apps, including Amplitude, Atlassian, Box, Canva, Docusign, Gamma, Linear, Miro, Notion, Replit, Webflow, and Zoom, with more on the way. But you aren’t just working with your favorite tools in a private chat; the real power comes when you share Slackbot’s output directly into a team channel. Suddenly, everyone can see the same real-time data and shape what happens next, together. Instead of switching between tools in isolation, Slackbot brings your team, your data, and your apps into one conversation.

Every app got its own AI in the last year, but none of them got any closer together or to your team — the work was happening in single player, private tabs. Our MCP client changes that: Slackbot becomes the connective layer for your entire stack, and because it lives in Slack, the work is multiplayer from the start. That's what makes this different.

• Rob Seaman, EVP and GM, Slack

From single-player silos to multiplayer momentum with the Slackbot MCP client

The Slackbot MCP client activates Slackbot as a universal connection point, allowing it to communicate with any app, whether built by Salesforce, partners, or your own team, through a natural conversation. This transforms Slackbot from a single-purpose agent into the ultimate AI teammate that consolidates your entire AI ecosystem into one chat.

You can now connect your apps directly to Slackbot. Simply make a request in plain language, and Slackbot handles the rest, routing it to the right specialized app, coordinating the steps, and delivering the final result. Instead of navigating all your tools, you get a conversational interface that actually finishes the work for you.

Beyond text, Slackbot also brings a rich, embedded experience of your favorite apps directly into your chat. By using the Model Context Protocol (MCP) and Slack’s Block Kit framework, these apps can instantly display interactive dashboards, forms, and previews right inside the conversation. Instead of an app sending you a flat, one-way alert that forces you to click out to a browser, Slackbot securely logs in to your third-party services for you, pulling in live, interactive data and letting you take real action right then and there.

• Actions, not just answers: With the new experience, powered by MCP, you can sign a document, update a ticket, or review a live dashboard right from your Slackbot conversation.
• Native Block Kit support (coming soon): Partner tools can now render rich visual components, including data tables and interactive carousels, directly inside your threads using the Block Kit framework. Best of all, data updates in real time with zero layout latency.
• Multiplayer execution: When you share Slackbot’s response into a team channel, individual tasks become a shared team advantage. Everyone can see the progress, validate the sources, and steer the outcome together.

Bring your own stack: plug-and-play integration

Before open standards, any custom integration required engineering teams to write brittle, low-level API code to connect every individual platform endpoint. This architecture created developer pain, ongoing maintenance, and heavy technical debt.

Standardizing on the open MCP allows Slack to eliminate custom integration bottlenecks. Any tool your team uses — whether it’s an internal database, a legacy system, or a bespoke app — can now connect to Slackbot via an MCP server. Instead of dealing with months of complex development, your team can bring your tools to life inside Slackbot in minutes.

Enterprise-grade governance and security

Deploying AI across an enterprise requires strict control over data. The MCP client respects Slack’s native compliance, security infrastructure, and permission controls out of the box.

The system applies user-specific data boundaries in real time: If someone doesn’t have credentials for a restricted database or a third-party project, Slackbot blocks the request automatically. IT administrators are equipped with a single, centralized surface within the application console to discover, install, manage, and audit user access approvals and data boundaries with total confidence.

Slackbot and your apps, working together

Through the new MCP registry in Slack Marketplace, you can connect your favorite tools and services to Slackbot and get more done without leaving Slack. Browse the registry, find the servers that fit your stack, and give Slackbot secure, real-time access to the data and systems your team already relies on.

Here’s what’s available today and coming soon:

Product and development

Access your specialized AI apps and agents that centralize system logs, track bugs, and manage incident responses directly inside triage channels. For example, an engineering lead can ask Slackbot, “What Linear tickets are blocking our release, and are there related PagerDuty incidents active?” Slackbot pulls a unified view of the blocker tickets and live incidents directly into the thread, letting developers reassign tasks via interactive buttons.
Apps available: Atlassian Rovo, Linear, MuleSoft, PagerDuty (coming soon), Replit, and Vercel

“The future of work isn’t a single AI assistant; it’s a connected ecosystem of intelligent tools. Teams should be able to achieve this with the tools they already trust and use every day. This is what Atlassian and Slack are building together. With Atlassian’s Teamwork Graph unifying your organization’s data across all your team’s tools, and Slackbot bringing that intelligence into the place teams talk and decide, we’re helping every team move faster while staying in lockstep.”

• Jamil Valliani, Head of AI Product, Atlassian

Document and content management

Connect your cloud storage and documentation platforms to Slackbot and let teams safely locate, search, and verify files without leaving the conversation. For example, a user can ask Slackbot, “Find the latest Q2 marketing pitch deck across our corporate files.” Slackbot searches all your connected storage platforms simultaneously, rendering matching assets as interactive visual thumbnails right in the channel thread.
Apps available: Box, Gamma, Notion (coming soon), and Webflow

“For over a decade, we’ve watched teams struggle with the same problem: An idea sparks in a conversation, then momentum dies in the gap before anything gets published. This integration puts Webflow directly inside that conversation. Now millions of teams can go from discussion to a published web experience without switching contexts, compressing the gap between idea and a live experience.”

• Dave Steer, Chief Marketing Officer, Webflow

Creative and design collaboration

Work with your design and visual ideation tools inside Slackbot and pull creative assets into public channels to turn scattered design feedback into fast team reviews. For example, a marketer can ask Slackbot, “Pull up the latest social media layouts from Canva and the campaign mood board.” Slackbot retrieves the graphics and presents them side-by-side as interactive visual blocks for instant team approval.
Apps available: Adobe (coming soon), Canva, Figma, and Miro

"Slack already connects to Canva AI. Bringing Canva to Slackbot continues that partnership, making it simpler for teams to carry context and intent into any work from the start --whether it's a status update document or an internal presentation-- without losing the thread along the way. Our goal is to make AI and design accessible, empowering people with easy-to-use tools that help them bring their ideas to life."

• Anwar Haneef, VP Ecosystem & Partnerships, Canva

Business operations and agreements

Integrate operational workflows from transactional, HR, and contract apps and agents directly into deal channels. For example, a sales rep can ask the Docusign app via Slackbot to draft an executive agreement. The contract’s key terms and signature lines render immediately in the channel, allowing stakeholders to modify terms using interactive buttons.
Apps available: Brex, Docusign, HiBob, Ironclad, Reclaim.ai by Dropbox, and Zoom

"Zoom’s open platform strategy is built on meeting customers where they work. By integrating our MCP server with Slackbot, we’re making it effortless for millions of users to access their Zoom meeting intelligence through natural conversation — no context switching required. This is what the agentic future of work looks like: AI that connects your tools and surfaces the right information at the right time."

• Brendan Ittelson, Chief Ecosystem Officer, Zoom

Visual collaboration and data analytics

Bridge the gap between raw data and team ideation by connecting your analytics and visual mapping tools directly to Slackbot. For example, a product manager can ask Slackbot, “Show me the checkout conversion drop-off trend from Tableau Next and pull up our Lucidchart user flow diagram so we can map out a fix.” Slackbot surfaces the real-time analytics chart alongside the visual blueprint as interactive, side-by-side blocks, letting the entire team diagnose the problem and brainstorm solutions collectively.
Apps available: Tableau Next (coming soon), Amplitude, Lucidchart, and Lucidspark

"Work moves too fast for teams to lose momentum jumping between conversations and creation tools. By combining the power of the Lucid MCP server and Slackbot, we’re making collaboration more immediate, contextual, and seamlessly integrated into how teams already work."

• Jamie Lyon, Chief Product and Strategy Officer, Lucid

Your entire workspace can now work with Slackbot

Work happens in conversation. Now the tools you rely on every day live there too. Instead of constantly pausing your chats to log in to five different websites, Slackbot brings your dashboards, documents, and designs directly to you in a single conversation.

It’s time to upgrade your daily workflow and experience what multiplayer work actually feels like. Check out the MCP registry in the Slack Marketplace to connect your favorite apps to Slackbot, and see how much faster your day moves when everything just works together.

The enterprise AI landscape is changing fast. Here’s what your security team needs to know about how Slack built MCP with trust at the foundation, not bolted on after the fact.

What is MCP, and why does it matter for your enterprise?

Model Context Protocol (MCP) is an open standard that lets AI agents connect to external tools and data sources without custom, one-off integrations. Think of it as USB for AI. One standardized interface that any tool can plug into.

For enterprises running Slack, this means Slackbot can now act as a central AI orchestrator of work. It can retrieve a Figma design, check a Jira ticket, pull up a DocuSign contract for signature, or query Salesforce CRM data, all in a single conversation, without users ever leaving Slack.

That kind of reach raises the question every CIO should ask first: how does this work securely at enterprise scale?

The short answer is that the MCP Client is built on the security infrastructure Slack already runs. There is no new trust model to evaluate. It’s an extension of the same app framework, admin controls, and data governance your organization relies on today, including the compliance certifications that governance rests on.

The architecture: how the MCP Client works in Slack

The Slackbot MCP Client uses remote HTTP/SSE transport only. Slackbot connects to MCP servers hosted on external infrastructure over HTTPS. It never spawns local processes with access to user devices or file systems. That’s a deliberate design decision, and it eliminates an entire class of local-access security risks before they can exist.

Every MCP server enters your Slack environment through three gates:

1. The developer registers.
   A partner or internal developer declares MCP server endpoints in their Slack app manifest, alongside a new mcp:connect OAuth scope.

2. An admin approves.
   The app goes through Slack’s standard App Directory review and admin approval process. Admins see exactly which MCP server domains are being requested before approving. No server enters a workspace without explicit admin sign-off.

3. The user connects.
   Once an app is approved, users see its MCP connectors in Slackbot. Connecting triggers an OAuth flow, and the resulting token is stored in Slack’s credential infrastructure.

One detail matters more than it sounds like it should: MCP servers are not a new top-level entity in Slack. They’re a capability of a Slack app. All of the distribution, marketplace review, admin approval, permissions, and lifecycle management your team already knows carries forward. No new playbook required.

That same existing posture carries the compliance side too. Because the MCP Client is an extension of the existing Slack platform, it operates under Slack’s existing certification portfolio, the same frameworks your security team has already evaluated:

• SOC 2 Type II and ISO 27001 cover the audited infrastructure MCP runs on, including access management, availability, and confidentiality.
• GDPR and HIPAA are covered under your existing Slack DPA and BAA. No addendum or separate agreement needed.
• FedRAMP is available via Slack Government for public sector customers.

Full documentation is available at the Slack Trust Center (slack.com/trust).

Authentication: three models, all built for enterprise

Slack supports three authentication strategies for MCP server connections, each suited to a different deployment scenario.

1. OAuth 2.0 with PKCE
   is the primary model for third-party MCP servers. Slack brokers a standard OAuth 2.0 flow with the external service and issues per-user tokens that admins can centrally revoke. PKCE support means even desktop clients authenticate without exposing tokens to interception.

2. Slack identity-based auth
   serves internal or Slack-first MCP servers. Slack sends signed requests with user context embedded, and the MCP server verifies the signature and maps it to its own user model. There’s no separate OAuth flow, and existing user mappings are preserved.

3. Static headers
   are available for internal and testing use only. These are workspace-scoped tokens without per-user identity, and they’re not recommended for production deployments that handle sensitive data.

Across all three models, every MCP call is made as the authenticated Slack user. Permissions, field-level security, sharing rules, and profile policies all apply at the source system, exactly as they would if that user opened the tool directly.

Admin controls: your organization stays in charge

Admins have granular control over the entire MCP surface in their workspace:

• Off by default.
  No server is available to users until an admin explicitly enables it through the standard app approval workflow.

• Domain-level visibility.
  Admins see exactly which MCP server domains an app requests before approving. Adding a new server from a different domain requires re-approval.

• Connector management.
  Users can view, connect to, and disconnect from individual MCP servers in Slackbot. Admins retain org-level override controls.

• Write tools sit behind a human.
  The initial release activates read-only tools. Write and delete tools will require explicit, per-action user confirmation before Slackbot proceeds. That friction is deliberate. It keeps humans accountable for consequential actions.

• App-level ACLs are GA.
  Admins can control the access to MCP server via App level ACLs. Coming soon – granular access control lists will let admins scope MCP server access by user, group, or role rather than all-or-nothing.

Data privacy and safety

AI in Slack, including Slackbot’s MCP-powered capabilities, operates under one consistent set of data principles. Customer data is never used to train LLMs, and prompts and outputs are not logged or visible to LLM providers. Existing permissions are respected at the time of generation, Slack personnel have zero internal access to your data, outputs are retained only as long as needed, and you keep ownership of your output data. Enterprise Key Management, International Data Residency, Discovery API requirements, legal holds, and your DLP and retention policies all extend automatically to AI-generated content, including MCP activity. Every AI action generates an audit log capturing the acting user, the action taken, and the relevant context.

On top of that governance layer, Slack runs a multi-layered safety framework on every AI interaction, also covering all MCP-powered Slackbot interactions. These safety measures include context engineering to reduce prompt injection risks, special handling for AI-generated URLs to prevent phishing attacks, output format validation, and real time content safety filters for risk-based blocking of malicious or harmful inputs.

Slack as the governance layer for your entire AI stack

The value here isn’t just how Slack secures Slackbot. It’s what Slack Enterprise+ enables across your whole AI tooling landscape. When users interact with AI tools through Slack, your existing enterprise controls become the universal governance layer:

• DLP policies
  govern the prompts and outputs shared by AI tools and agents, including Slackbot interactions.

• Audit logs
  capture Slackbot usage and third-party AI usage whenever MCP tools interact with Slack data or take actions in Slack.

• Full data export and search query export
  give compliance and security teams visibility into Slackbot conversations and the exact prompts teams are running.

Instead of configuring separate governance in every AI tool your organization adopts, Slack becomes the single place where those controls are enforced consistently. For a security team managing a growing portfolio of agentic tools, that’s a real architectural advantage.

Bottom line for the CIO

MCP in Slack isn’t a new security surface. It’s an extension of the security model you already operate, backed by the certifications already covered above. The admin approval gates, OAuth-based authentication, per-user permission enforcement, audit logging, DLP integration, and data residency controls all carry forward.

What’s new is the capability. Your organization’s AI assistant can now reach across every tool in your stack and take real action on behalf of your people, without leaving the secure environment you’ve already invested in building.

The question isn’t whether MCP is secure enough for your enterprise. It’s whether your enterprise is ready to work the way your people already want to.

Additional resources

• Slack Trust Center — slack.com/trust
• Guide to the Slack MCP server — slack.com/help

Build your Slackbot memory

Slackbot will now save relevant context from your Slack activity to use in responses and drafted content. You can also import memory from other AI tools to get Slackbot up to speed faster.

Talk instead of typing

Click or tap the microphone icon in the message field to dictate messages. Slackbot will respond with a written message, but will be able to send spoken replies in the future.

Tasks tab

Open the new Tasks tab to view and manage all of your tasks.