Statsig runs feature flags and online experiments and measures their effect on product metrics. Connecting Statsig to clariBI puts experiment results and feature-gate exposure next to the revenue and usage data those experiments are meant to move.
Why connect Statsig
Experiment readouts usually stay inside the experimentation tool, separate from the financial and retention numbers leadership actually tracks.
With Statsig connected, you can ask "Which experiments shipped this quarter and what did they do to activation?", "What is the exposure split on the new-onboarding gate?", or "Did the checkout test move revenue per user?" and the AI engine reads the result live.
How the connection works
clariBI talks to Statsig through its hosted MCP server at https://api.statsig.com/v1/mcp. Authentication uses an OAuth flow that clariBI registers itself for (no developer console setup on your side). Tokens stay encrypted server-side and never leave clariBI in clear form.
sequenceDiagram
actor U as You
participant C as clariBI
participant V as Statsig
U->>C: Click Authorize with Statsig
C->>V: Open OAuth authorization
V-->>U: Grant read access?
U->>V: Approve
V-->>C: Authorization code
C->>V: Exchange code for tokens
V-->>C: Access + refresh tokens
C->>C: Encrypt and store credentials
C-->>U: Connection ready
Available tools
clariBI exposes the read-only Statsig tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Statsig cannot modify data on the vendor side.
The exact tool inventory depends on the Statsig features your account has access to. After connecting, try a few natural-language questions to see what Statsig data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Statsig, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.
sequenceDiagram
actor U as You
participant C as clariBI
participant AI as AI engine
participant V as Statsig
U->>C: Ask a question about experimentation and feature-flag data
C->>AI: Plan the analysis
AI->>V: Call the right tool
V-->>AI: Tool result
AI->>AI: Summarize and chart
C-->>U: Answer plus visual
Setting up the connection
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Statsig card.
- Click Authorize with Statsig.
- Sign in to Statsig in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI connects through Statsig's OAuth flow and inherits the connected user's project access. The catalog exposes read tools only (reading gates, experiments, metrics, and config); clariBI never starts, stops, or edits an experiment or flag. Disconnect anytime from Settings → Integrations in clariBI.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "No experiments returned" | The connected user is scoped to a different Statsig project, or the experiments live under a project the token cannot see. | Confirm the project in Statsig and that your user has access, then reconnect. |
| "Metric values look empty" | The metric has not accumulated exposures yet, or the analysis window predates the experiment start. | Widen the time range or wait for the experiment to gather exposures. |