Pydantic Logfire is the OpenTelemetry-native observability platform from the Pydantic team — designed for AI applications with first-class trace, metric, and log support. Connecting Logfire to clariBI brings telemetry into your AI analyses.
Why connect Logfire
LLM-call observability questions ("what was the average token cost per request yesterday?") usually require dashboard hopping. With Logfire connected the AI engine queries the OTel datastore directly.
You can ask "Show me the slowest API endpoints in the last hour", "Trace count by status code today", or "Top 10 errors in the agent service" and the AI engine pulls the answer from Logfire.
How the connection works
clariBI talks to Logfire through its hosted MCP server at https://logfire-us.pydantic.dev/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 Logfire
U->>C: Click Authorize with Logfire
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 Logfire 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 Logfire cannot modify data on the vendor side.
The exact tool inventory depends on the Logfire features your account has access to. After connecting, try a few natural-language questions to see what Logfire data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Logfire, 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 Logfire
U->>C: Ask a question about OpenTelemetry observability 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 Logfire card.
- Click Authorize with Logfire.
- Sign in to Logfire 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. clariBI requests the project:read scope. EU-region customers should connect via the Custom MCP catalog row pointing at https://logfire-eu.pydantic.dev/mcp until the wizard supports per-region selection.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Region mismatch" | Your Logfire project lives in the EU region but this catalog row points at the US endpoint. | Use the Custom MCP catalog row with https://logfire-eu.pydantic.dev/mcp as the endpoint URL. |