Slack Expands Platform to Power Secure, Context-Aware AI Apps and Agents Built on Conversational Data

The new real-time search API and Model Context Protocol server give developers flexible, secure access to Slack's conversational data.

With these innovations, partners and developers can build AI apps and agents that tap into customers' unstructured conversational data, accelerating employee productivity while meeting enterprise governance and control requirements.

Leading innovators - including Anthropic, Google, Perplexity, Writer, Dropbox, Notion, Cognition Labs, Vercel, and Cursor - are already building on these innovations with new AI Slack apps and agents available in the Slack Marketplace.

Thousands of companies are racing to build agents, but most run into the same obstacle: how to make them actually useful in the day-to-day flow of work. Agents run on data, but what makes them powerful is context, and the richest context comes from conversations. Conversational data is the gold of the agentic era, yet it's been locked away in unstructured messages and chats, largely out of reach for employees, let alone applications. Enter Slack, the work operating system for the agentic enterprise.

Today, we're announcing the next evolution of the Slack platform, giving partners and developers the tools to securely connect AI with the rich corpus of customer-owned and -controlled conversational data in Slack. With a new real-time search (RTS) API, a Model Context Protocol (MCP) server, and enhanced developer tools like prebuilt Block Kit Tables, Slack provides secure, flexible, agent-ready access to conversational data. This context enables agents to move beyond generic responses to deliver context-aware, user-specific conversations, making AI more relevant, more accurate, and far more powerful in unlocking productivity.

Some of the world's most innovative companies, like Anthropic, Google, Perplexity, Writer, Dropbox, Notion, Cognition Labs, Vercel, Cursor, and others, are already building on these capabilities to deliver compelling AI applications and agents, all living natively in Slack. By securely tapping into Slack's conversational data, these companies - and thousands more - are bringing intelligence directly into the flow of work to accelerate growth. This isn't just about integrations; it's a new way to build and a new way to work.

Slack: The Natural Home for Modern AI Apps and Agents

By building agents directly in Slack, developers can overcome another problem plaguing the modern enterprise: endless fragmentation leading to low app adoption. There are over 200,000 SaaS companies in the world, and an average enterprise uses over 1,000 applications. The result: countless hours lost, with employees clicking between apps, endless copying and pasting, and context switching draining productivity by up to 40%. No surprise that nearly half of SaaS licenses go unused as shelfware.

There's a better way, and it's as natural as talking to a teammate. Imagine a seller asking an agent to update CRM records, an employee resolving an IT issue without filing a ticket, or a marketing leader analyzing campaign performance without pulling a single report.

That's only possible with a platform that's conversational, agent-based, and built on conversational data. By building AI-powered applications directly in Slack, developers and partners help organizations unify their tech stack - making Slack the 2% of your IT budget that maximizes the return on the other 98%.

Developers and partners are taking advantage of the Slack platform's breadth to create AI apps and agents directly in the flow of work, allowing companies to:

• Unlock Unstructured Data: Slack is enabling organizations to safely and securely tap into the vast amounts of collective knowledge stored in Slack conversations to enrich AI and agents, saving customers an average of 97 minutes a week.
• Accelerate Decision-Making: By connecting app data, like Agentforce Sales or Workday, with Slack conversations, the platform provides complete context, enhancing search and AI for faster insights and action, resulting in 37% faster decision-making across teams and 36% faster responses to customers.
• Increase Productivity: Businesses most able to use AI have three times higher growth in revenue per employee. By integrating apps and agents directly into human workflows, Slack eliminates context switching, enabling teams to cut hours of manual research and get straight to action.
• Solve the Adoption Gap: Slack brings partner and developer apps directly into the flow of work, helping overcome one of developers' biggest distribution challenges - getting employees to actually use them - by making apps accessible where employees are already working. Over 1.7 million apps are actively used in Slack each week, and 95% of those users say using an app in Slack makes those tools more valuable.
• Ensure Security and Compliance: With Slack's enterprise-grade security, privacy features, and granular permissions, businesses can safeguard their data while providing a secure foundation for agentic collaboration.

Salesforce Executive Perspective

"The future of work is undeniably agentic, and the success of AI depends on its seamless integration into human workflows," said Denise Dresser, CEO, Slack. "Our latest Slack platform innovations create the secure, data-rich environment necessary for AI agents to become trusted companions. We make it simple for customers and partners to build their AI solutions directly into Slack so that work is more connected, intelligent, and productive than ever before."

The future of work is undeniably agentic, and the success of AI depends on its seamless integration into human workflows.

A Deeper Look: Powering Trusted, Context-Aware AI in Slack

Slack fundamentally redefines user interaction by establishing AI agents as trusted companions. Slack's expanded developer platform is purpose-built for agentic AI, making it easy for any company to build powerful, custom AI agents that can access rich, contextual conversational data to get more done, securely.

The real-time search (RTS) API and Model Context Protocol (MCP) server provide secure data access on your terms for developers and third parties:

• The RTS API gives apps real-time access to one of a company's most valuable assets: the rich, contextual conversational data within Slack. By surfacing the most current discussions, files, and channels, the RTS API makes the Slack platform more flexible and empowers AI to act on information in context. It unlocks your organization's collective intelligence, securely connecting agents to conversations and decisions that were once trapped in silos. The RTS API is designed with enterprise security at its core, enabling tools to interact with customers' conversational data without needing to bulk download it or store it elsewhere. It always respects existing access permissions and retrieves data in a focused, use-case-driven way, returning only the specific messages or files relevant to a query. The result: AI agents and apps get the precise, contextual information they need - nothing more, nothing less.
• The MCP server simplifies and standardizes how large language models (LLMs), AI apps, and agents discover contextual information and execute tasks on behalf of Slack users, reducing complexity for developers. With its unified communication layer between the LLM and Slack, it establishes a universal way for AI systems to connect to data sources and tools. Fragmented integrations are replaced with a single, consistent protocol that adheres to the user's specific permissions. Developers don't have to manually define every possible task an agent can perform or implement complex, service-specific integrations for each LLM.

The RTS API and MCP server transform how partners build on Slack by giving their AI-powered applications secure access to real-time conversational data. With this foundation, developers can move beyond basic integrations to create contextual, intelligent experiences that automate complex workflows. Their agents can now search, analyze, and act on Slack data to deliver more accurate, relevant, and personalized outcomes - reducing hallucinations and increasing reliability. The result: smarter, more stable agents that users can trust and adopt at scale.

Foundational to all of this innovation is Slack's enterprise-grade approach to privacy and security, helping to ensure teams can build intelligent, contextual AI experiences without compromising trust or interoperability. And it's not just partner apps in the Slack marketplace: Customers building custom applications for internal use can leverage these powerful capabilities and, as always, maintain complete access to their Slack data, with the freedom to use it however they choose.

In addition, the Slack platform continues advancing the fundamental building blocks available to admins and developers with new innovations:

• Slack Work Objects: Developers can now build apps that deliver dynamic experiences by connecting app data directly to Slack conversations through rich app previews that include everything from file descriptions to embedded images. Slack Work Objects standardize how third-party data - like detailed information, images, and documents - is displayed in Slack, creating a much deeper connection between apps and conversations. Teams can‌ also take action, like marking Asana tasks as complete, without ever having to leave the Slack workspace. This allows users to communicate, share, and act on work without switching applications, directly within Slack.
• Agentic Developer Tools: Developers have everything they need to build and customize Slack for their business. From apps and agents to automated workflows, new capabilities include AI best practices, prebuilt Block Kit Tables, and updated resources like the CLI for Bolt apps. These upgrades streamline the entire development lifecycle, from the first line of code to the finished end-user experience, making it easier than ever to build for the agentic era.

All of our third-party solutions are available in the Slack Marketplace, which takes a centralized approach to the control, security, and distribution of apps and agents. Alongside Slack functionality, the marketplace apps and third-party integrations play a crucial role in creating a unified ecosystem for human-AI collaboration. The marketplace makes it easier than ever for customers to discover tools that customize and securely extend the functionality of Slack to fit their teams' needs.

Altogether, these new capabilities and tools fuel a dynamic ecosystem of AI innovators like Anthropic, Google, Perplexity, Writer, Dropbox, and Notion that are building and integrating powerful AI agents and applications directly on the Slack platform.

A Robust Ecosystem of AI Innovation

Leading AI innovators, including Anthropic, Google, and Perplexity, are building powerful AI agents directly on the Slack platform, leveraging the new capabilities to solve complex customer problems.

• Anthropic's Claude : This integration brings the power of Claude directly into Slack workspaces, allowing teams to collaborate with Claude through direct messages, an AI assistant panel, or @ mentions in threads - with access to web search, data source connections, document analysis, and other capabilities available through their Claude accounts. By connecting Slack data to the Claude app, users unlock even deeper insights, enabling Claude to search across workspace channels, messages, and files, creating a seamless AI experience that works wherever teams need it.
• Google Agentspace : Google Agentspace is a single, secure platform to build, manage, and adopt AI agents at scale. It brings together data and context from across productivity tools, turning the organization's knowledge into insights and actions. The Agentspace integration with Slack RTS API creates a seamless information flow, allowing users to access these deeper insights both via Agentspace agents inside Slack or by using Agentspace fueled by live Slack data.
• Dropbox Dash : Dropbox uses the RTS API to provide real-time insights across Slack and Dropbox Dash, giving customers instant access to their content while ensuring permissions and security remain intact.
• Perplexity Enterprise : Perplexity brings the web and your team's conversations together, delivering intelligent, context-aware answers. Whether in Slack or Perplexity, you can ask questions, reference discussions, and access real-time research without losing context.
• Notion AI : Notion AI Slack app allows shared customers to ask questions about threads, conversations, or updates they might have missed. New platform features like the RTS API enable Notion users to search content from public channels, private channels, and, with appropriate permissions, DMs to make sure that their work in Notion reflects conversations happening in Slack.

What Our Customers and Partners Are Saying

• Anthropic: "Businesses today conduct their most important conversations across multiple Slack channels, creating a wealth of institutional knowledge that hasn't been accessible to AI assistants like Claude. Slack's real-time search API changes that - Claude can now draw context from your team's actual discussions to provide answers grounded in your real work, then deliver those insights directly back into your workflow. This integration enables Claude to provide trusted intelligence that's aligned with how your team actually operates." - Scott White, Head of Product, Claude
• Google: "Organizations depend on Google Agentspace and Slack for productivity and collaboration. Now, customers can embed insights from Agentspace directly into Slack and use Slack conversations to enhance workflows within Agentspace, creating a more seamless flow of information that enhances everyday work." - Maryam Gholami, Senior Director, Product Management, Google Cloud
• Perplexity: "Perplexity is redefining search as a conversational, transparent discovery experience. By connecting to Slack through the MCP server, we can now ground queries in the context of team conversations - helping users surface answers that are not only accurate but directly relevant to their work. This broadens the use cases users can tackle with Perplexity and the confidence they feel in the results they get. Slack has been a fantastic partner in making this possible, with shared focus on security, compliance, and user trust." - Frank te Pas, Head of Enterprise Product, Perplexity
• Writer: "By connecting Slack and Writer, we can collapse the distance between discussion and action. Slack provides the real-time pulse of an organization - the brainstorms, the decisions, the customer feedback. WRITER provides the agentic intelligence to transform that pulse into outcomes. Now, teams can instantly generate project plans, draft on-brand communications, and automate next steps, all grounded in the context of their work. It's how we're giving people a trusted partner in driving work forward." - Maureen Little, SVP, Partnerships & Ecosystem, Writer
• Notion AI: "The best work happens when context and execution aren't separate. With Notion AI and Slack together, teams can turn every conversation into action." - Erica Anderson, Chief Revenue Officer, Notion
• Dropbox: "Customers need practical AI tools that are powerful, secure, and seamlessly integrated into their workflows. Through our collaboration with Slack on the real-time search API, we're delivering real-time insights across Slack and Dropbox Dash, giving customers instant access to their content while ensuring permissions and security remain intact. Instead of dealing with the friction of switching between apps, customers can stay focused on what matters most - doing their best work." - Josh Clemm, VP, Engineering, Dropbox

Availability

The RTS API and Slack MCP server are currently available in closed beta, with general availability in early 2026. Third-party AI agents using the capabilities are available on the Slack Marketplace today. Slack Work Objects will be generally available to all developers in late October. New agentic developer tools are available now.

Learn more:

The above is intended for informational purposes. Please don't rely on this information in making your purchasing decisions. The development, release, and timing of any products, features, or functionality remain at the sole discretion of Salesforce and are subject to change.