Keboola is the data-platform many engineering teams use for ELT pipelines, transformations, and shared data infrastructure. Connecting Keboola to clariBI surfaces every project, table, and pipeline run into your AI analyses.
Why connect Keboola
Pipeline observability questions ("which Keboola jobs failed in the last 24h?") usually require opening the Keboola UI.
With Keboola connected, you can ask "List Keboola projects sorted by row volume", "Show me the latest run of the customer-pipeline transformation", or "Which orchestration jobs failed yesterday?" and the AI engine pulls the answer.
How the connection works
clariBI talks to Keboola through its hosted MCP server at https://mcp.keboola.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 Keboola
U->>C: Click Authorize with Keboola
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 Keboola 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 Keboola cannot modify data on the vendor side.
The exact tool inventory depends on the Keboola features your account has access to. After connecting, try a few natural-language questions to see what Keboola data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Keboola, 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 Keboola
U->>C: Ask a question about Keboola pipelines, tables, and project metadata
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 Keboola card.
- Click Authorize with Keboola.
- Sign in to Keboola 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
OAuth scoping is granted at authorize time on the Keboola consent screen. clariBI restricts itself to read-only tools — no pipelines can be triggered, paused, or modified through this connection. EU/regional customers using mcp.us-east4.gcp.keboola.com, mcp.eu-central-1.keboola.com, mcp.north-europe.azure.keboola.com, or mcp.europe-west3.gcp.keboola.com should connect via the Custom MCP catalog row with the region-specific URL.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Project selection missing" | Your Keboola account has multiple projects. | Pick one project in Keboola before authorizing. |