Anthropic Unveils Interactive Claude Apps for Slack and Workplace Integration

Claude users can now access interactive apps directly within the chatbot, a new feature introduced by Anthropic on Monday.
Reflecting Anthropic's business-centric approach, the initial launch includes primarily workplace tools such as Slack, Canva, Figma, Box, and Clay, with a Salesforce integration planned for the near future. For each enabled app, Claude can access a logged-in session, allowing users to perform tasks like sending Slack messages, creating charts, or retrieving cloud-based files.
"Dedicated visual interfaces significantly enhance data analysis, content creation, and project management," Anthropic stated in a blog post announcing the update. "When paired with Claude's reasoning, this combination accelerates work and iteration beyond what either could achieve independently."
The feature is accessible to Pro, Max, Team, and Enterprise subscribers, but not to free users. Eligible accounts can enable the tools at claude.ai/directory.
This system resembles OpenAI's Apps platform, launched in October, which also supports interactive third-party tools. Both integration frameworks are built on the Model Context Protocol (MCP), an open standard Anthropic introduced in 2024. MCP added support for apps in November, incorporating developments from both organizations.
The new apps gain considerable power when used with Claude Cowork, a versatile agent tool released by Anthropic last week. Developed from Claude Code, Cowork allows users to assign complex, multi-stage tasks involving large, open-ended datasets—work that previously required command-line expertise. When combined with apps, Cowork can be authorized to access cloud storage or active projects. For instance, it could modify a marketing asset in Figma or utilize updated data from a company's Box account.
App integration is not yet available in Cowork at launch, but Anthropic confirmed it is "coming soon."
Agentic systems can behave unpredictably, and Anthropic's own safety guidelines for Cowork advise users to supervise the agent actively and avoid granting excessive permissions.
"Exercise caution when providing access to sensitive materials such as financial documents, credentials, or personal records," the company recommends. "Consider setting up a specific working directory for Claude instead of allowing broad system access."
Related article
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber
Related Special Topic Recommendations
Comments (0)
0/500

Claude users can now access interactive apps directly within the chatbot, a new feature introduced by Anthropic on Monday.
Reflecting Anthropic's business-centric approach, the initial launch includes primarily workplace tools such as Slack, Canva, Figma, Box, and Clay, with a Salesforce integration planned for the near future. For each enabled app, Claude can access a logged-in session, allowing users to perform tasks like sending Slack messages, creating charts, or retrieving cloud-based files.
"Dedicated visual interfaces significantly enhance data analysis, content creation, and project management," Anthropic stated in a blog post announcing the update. "When paired with Claude's reasoning, this combination accelerates work and iteration beyond what either could achieve independently."
The feature is accessible to Pro, Max, Team, and Enterprise subscribers, but not to free users. Eligible accounts can enable the tools at claude.ai/directory.
This system resembles OpenAI's Apps platform, launched in October, which also supports interactive third-party tools. Both integration frameworks are built on the Model Context Protocol (MCP), an open standard Anthropic introduced in 2024. MCP added support for apps in November, incorporating developments from both organizations.
The new apps gain considerable power when used with Claude Cowork, a versatile agent tool released by Anthropic last week. Developed from Claude Code, Cowork allows users to assign complex, multi-stage tasks involving large, open-ended datasets—work that previously required command-line expertise. When combined with apps, Cowork can be authorized to access cloud storage or active projects. For instance, it could modify a marketing asset in Figma or utilize updated data from a company's Box account.
App integration is not yet available in Cowork at launch, but Anthropic confirmed it is "coming soon."
Agentic systems can behave unpredictably, and Anthropic's own safety guidelines for Cowork advise users to supervise the agent actively and avoid granting excessive permissions.
"Exercise caution when providing access to sensitive materials such as financial documents, credentials, or personal records," the company recommends. "Consider setting up a specific working directory for Claude instead of allowing broad system access."
Stripe to Acquire OpenRouter as AI Model Routing Gains Momentum
Stripe has agreed to acquire OpenRouter, an AI model-routing platform that gives developers access to hundreds of models through a single interface. The deal adds model selection and routing to Stripe’s existing work around AI usage and token-based b
Former OpenAI Researcher Barrett Zoph Returns to Google to Support Gemini Development
Barret Zoph, who previously abruptly left and joined OpenAI due to a disagreement with Thinking Machines Lab CEO Miriam Mularati, has once again changed employers. Alphabet's Google announced that Zoph will return as Vice President of Research, bring
How Recursive Intelligence Raised $335M at $4B Valuation in 4 Months
The co-founders of startup Ricursive Intelligence seemed destined to be co-founders.Anna Goldie, CEO, and Azalia Mirhoseini, CTO, are so well-known in the AI community that they were among those AI engineers who “got those weird emails from Zuckerber





Home






