Anthropic Launches Interactive Claude App, Integrates with Slack and Workplace Tools

Claude users can now leverage interactive applications directly within the chatbot interface, thanks to a new feature announced by Anthropic on Monday.

Aligning with Anthropic's enterprise focus, the initial suite of apps consists primarily of workplace tools, including Slack, Canva, Figma, Box, and Clay, with Salesforce support expected soon. Each application enables a logged-in service instance that Claude can access, allowing users to perform tasks like sending Slack messages, generating graphics, or retrieving cloud files, depending on the specific apps enabled.

"Analyzing data, designing content, and managing projects are more effective within dedicated visual interfaces," Anthropic stated in a blog post announcing the feature. "By combining Claude's intelligence, you can work and iterate faster than using any tool alone."

The new functionality is available to Pro, Max, Team, and Enterprise subscribers but is not accessible to free users. Eligible users can activate these tools at claude.ai/directory.

This system resembles OpenAI's application framework, launched in October, which also supports interactive third-party tools. Both integration systems are built upon an open standard introduced by Anthropic in 2024: the Model Context Protocol (MCP). MCP, which added application support in November, draws from the work of both companies.

The new applications will be particularly powerful when integrated with Claude Cowork, the multi-functional agent tool launched by Anthropic last week. Built on Claude Code, Cowork allows users to assign multi-step tasks that rely on large, open-ended datasets—tasks that previously required terminal commands. Combined with the new app functionality, Cowork can be granted access to cloud files or active work projects. For instance, it could update marketing graphics in Figma or utilize new data from a company's Box instance.

Applications were not available at the time of Cowork's launch, but Anthropic indicated that integration is "coming soon."

Agent systems can behave unpredictably. Anthropic's own safety documentation advises users to closely monitor the agent when using Cowork and to avoid granting any unnecessary permissions.

"Exercise caution when granting access to sensitive information such as financial documents, credentials, or personal records," the company recommends. "Consider creating a dedicated workspace folder for Claude instead of granting broad access permissions."