Changelog

Saved Explorations

You can now save explorations and return to them later. Saved explorations appear in the Workspace alongside workbooks and dashboards, and can be organized into folders.

Saved explorations are integrated with the Google Sheets and Excel add-ons. Save an exploration in Cube and apply it directly from the add-on, or create one in the add-on and update it from your Workspace.

Other improvements and fixes:

• Folder-inherited permissions are now displayed in the share dialog
• Google Sheets and Excel add-on UIs updated to match the Explore experience
• Added support for GPT 5.3 and GPT 5.4
• Introduced Auto option for LLM selection in agent settings
• Added option to trim trailing zeros in number formatting

SCIM, or System for Cross-domain Identity Management, allows for the automation of user provisioning in your Cube account.

With SCIM enabled, user accounts can be automatically created, updated, and suspended based on your IDP settings—eliminating the need for manual account management in Cube.

Custom user attributes can be synced from your identity provider to Cube, allowing you to fully centralize your user management.

This integration helps ensure that your team's access stays in sync with your organization's directory.

Other improvements and fixes:

• The AI agent is now available in the data source connection step and can help you connect to data sources.
• Clearer error messages for data model misconfigurations.
• Added a configuration option to set the timeout for agent queries to semantic models.

You can now organize workbooks into folders to better structure your analytics content. Grant permissions at the folder level, and all workbooks inside will automatically inherit these permissions, making it easier to manage access across related content.

This feature improves content organization and discovery, and represents our first step toward building a robust analytics content discovery platform.

Create Dashboards from Chat

You can now ask the AI agent to create a dashboard directly from Analytics Chat conversations. Your entire conversation can be turned into an interactive dashboard, making it easy to convert your data discussions into shareable analytics content. This feature requires access to workbooks.

Other improvements and fixes:

• Improved refresh states for KPI, Map, and HTML charts
• Dashboard filters now properly handle missing dimensions
• Added support for Bedrock inference profiles
• Updated IDE layout and fixed various issues
• Updated dashboard filters for consistent look and feel
• Agents can now be hidden from iframes via settings
• Fixed timezone shift in Excel add-in

The Model Context Protocol (MCP) enables AI applications to securely access external data sources and tools. Now users can connect AI assistants like Claude to the Cube MCP server, providing a way to explore your data through natural language.

Cube MCP server is compatible with all modern AI clients that support MCP: Claude, ChatGPT, Cursor, Codex, and more. Users can configure what deployments and agents to use for MCP server.

Navigate to Admin → MCP Server to get started.

Other improvements and fixes:

• Chat history now displays the full queries, including data and SQL
• Generated SQL is shown in Explore, Workbooks, and Analytics Chat alongside Semantic SQL
• Dimensions and measures descriptions are now being surfaced in Explore and Workbooks
• Updated branch switcher

You can set up Cube dashboards to automatically update on a schedule. When a scheduled refresh is triggered, the widgets on the dashboard are queried in the background, refreshing Cube's in-memory cache. This warms up dashboards so they load instantly when users open them, eliminating wait times for data to load.

Access scheduled refreshes from the dashboard builder or published dashboard by clicking the calendar icon, which opens the scheduled refreshes sidebar. From this sidebar, you can create new schedules, modify existing ones, or remove schedules you no longer need.

Snowflake Semantic Views integration

Cube now supports bi-directional integration with Snowflake Semantic Views. This integration enables you to author views in Cube and use them in Snowflake, or work with Snowflake semantic views directly in Cube. This ensures consistency between your Cube definitions and Snowflake's semantic layer, allowing teams to work in their preferred environment.

From the IDE, users can pull semantic views from Snowflake and turn them into cubes and views in Cube. The pull integration generates code files with cube and view definitions in your Cube repository, making it easy to work with existing Snowflake semantic views. Alternatively, you can push Cube views into Snowflake as native semantic views. The push integration creates DDL from Cube's definitions and executes it in Snowflake, creating Snowflake Semantic Views that match your Cube schema.

Other improvements and fixes:

• Explore can be opened directly from IDE now
• Analytics chat suggestions are available in embedded chat
• Views switching and redo/undo in Explore are fixed
• Dashboard and analytics chat iframe embedding height is fixed