MCP (V0)
Kubit’s MCP makes it incredibly easy to work with your data directly inside AI tools like Cursor and Claude. Instead of switching between platforms, you can simply ask to explore your data model, create reports, review results, export underlying data, or search for existing reports and dashboards—all from within your AI workspace.
The initial release includes everything needed to get started: understanding your schemas, generating new analyses on the fly, accessing raw data, and locating existing insights instantly. Kubit MCP is available in Cursor and Claude, with additional platforms coming soon.
Overall, MCP helps teams move faster, stay in flow, and bring Kubit’s analytics directly into your everyday workflow.
More about the Kubit MCP can we found here, and we are also listed in the official MCP Registry.
Chart Builder
We moved the builder to the left-hand side to create a more efficient and comfortable workflow. This layout lets users view the builder and the report side by side, reducing scrolling fatigue and speeding up interactions. The new Chart Settings tab is now integrated directly into the builder, allowing users to refine and customize visualizations without ever losing sight of the chart itself. This update also frees up significantly more space for the visual—an improvement that becomes even more impactful with the expanded visualization real estate coming in the next release.
Flow Analysis (Available on Clickhouse)
Kubit’s new Flow Analysis is now fully supported on ClickHouse. Teams using Clickhouse can now explore user journeys, identify drop-offs, and understand conversion patterns.
Compare - Available in Funnels
Kubit’s conversion funnels now include a powerful compare to previous period feature, letting teams instantly see how funnel performance has changed over time. By viewing step-by-step improvements or drop-offs against the prior period, it becomes much easier to validate product changes, spot regressions, and understand shifts in user behavior. This unlocks use cases like measuring the impact of new features or campaigns, monitoring onboarding improvements, and tracking long-term funnel trends with clarity.
AI Detect - GA
Kubit’s enhanced AI Detect provides stronger, more reliable anomaly detection across three key categories:
Freshness — identifies missing or delayed data
Distribution — detects abnormal value shifts compared to historical patterns
Volume — flags unusual changes in record counts
For daily reports, Kubit analyzes results against multiple reference points including the long-term historical mean, short-term windows, and same-day comparisons to ensure higher accuracy.
Deeper Historical Context
Even if a dataset only contains a small number of days, Kubit uses the full execution history of scheduled reports—meaning months of past runs can be used to detect anomalies more reliably.Flexible Configuration
You can now enable or disable anomaly detection at the report or dashboard level.Customizable Visibility
Choose whether to show or hide anomalies directly within each report or dashboard.Streamlined Alerts
Slack notifications now include a clean, summarized view of all detected issues for quick review.