Tavily is the AI-grade search and web-extraction service built for retrieval-augmented generation. Connecting Tavily to clariBI surfaces live web research, structured page extraction, and crawl/map workflows as first-class tools for AI analyses.
Why connect Tavily
Research questions ("what did our category leaders launch this quarter?") usually mean dozens of browser tabs. Tavily collapses search + extraction + citation into one tool.
You can ask "Find recent press about competitor X", "Extract the pricing table from this product page", or "Map the support-docs site for competitor Y" and the AI engine routes through Tavily.
How the connection works
clariBI talks to Tavily through its hosted MCP server at https://mcp.tavily.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 Tavily
U->>C: Click Authorize with Tavily
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 Tavily 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 Tavily cannot modify data on the vendor side.
The exact tool inventory depends on the Tavily features your account has access to. After connecting, try a few natural-language questions to see what Tavily data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Tavily, 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 Tavily
U->>C: Ask a question about live web search and structured page extraction
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 Tavily card.
- Click Authorize with Tavily.
- Sign in to Tavily 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 Tavily consent screen. clariBI requests read-only search and extraction scopes — no content is written to Tavily.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Quota exceeded" | Tavily enforces per-plan per-month query quotas. | Wait for the quota reset, narrow your query, or upgrade your Tavily plan. |