DevCycle is an OpenFeature-native feature management platform. Teams wrap features in flags, define variations and variables, target them at audiences, and roll them out gradually across environments. Connecting DevCycle to clariBI makes the flag estate measurable: how many flags exist, where each one sits in its rollout, and what changed in the audit trail.
Why connect DevCycle
Flags accumulate faster than they retire, so stale flags and half-finished rollouts hide across environments with no single inventory to audit.
With DevCycle connected, you can ask "How many flags are fully rolled out versus still partial?", "Which flags have not changed in 90 days and could be retired?", or "What targeting changes shipped to production last week?" and the AI engine reads it live.
How the connection works
clariBI talks to DevCycle through its hosted MCP server at https://mcp.devcycle.com/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 DevCycle
U->>C: Click Authorize with DevCycle
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 DevCycle 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 DevCycle cannot modify data on the vendor side.
The exact tool inventory depends on the DevCycle features your account has access to. After connecting, try a few natural-language questions to see what DevCycle data clariBI can pull.
Data flow during analysis
When you ask a question that maps to DevCycle, 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 DevCycle
U->>C: Ask a question about feature flag and rollout 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 DevCycle card.
- Click Authorize with DevCycle.
- Sign in to DevCycle 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 DevCycle's OAuth flow and inherits the connected user's project and environment access. The catalog exposes read tools only (reading features, variables, variations, environments, targeting rules, and audit history); clariBI never creates, edits, or deletes a flag or targeting rule. Disconnect anytime from Settings → Integrations in clariBI.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "No features returned" | The connected user is scoped to a different DevCycle project, or the project has no features yet. | Confirm the project in DevCycle and that your user has access, then reconnect. |
| "Rollout percentages look stale" | The targeting was changed after the analysis window, so the read reflects an earlier state. | Re-run the analysis, or widen the window to include the most recent targeting change. |