How to build Arize Phoenix dashboards in Metabase

Arize Phoenix is an open-source, OpenTelemetry-native LLM tracing and evaluation platform from Arize that you can self-host anywhere. Metabase is where you turn that LLM telemetry into shared, trustworthy dashboards. This guide covers two complementary paths: a lightweight MCP + CLI route that pulls live data with the Phoenix MCP server and loads a CSV into Metabase with the Metabase CLI, and a durable pipeline route that syncs Arize Phoenix rollups into a database so you can build dashboards anyone can read.

How do you connect Arize Phoenix to Metabase?

Most teams combine both routes: use quick exports and CLI uploads for a fast first pass, then move recurring cost and quality reporting to a warehouse-backed model.

What can you analyze from Arize Phoenix data in Metabase?

Each view below is built from traces and spans, plus the experiments, datasets, and annotations your sync exposes:

• Trace volume and latency by project
• Token usage by model and app
• Span error and exception trends
• Eval scores from experiments
• Session and user activity

Which Arize Phoenix dashboards should you build in Metabase?

How do you use the Phoenix MCP server with the Metabase CLI?

Pair the Phoenix MCP server with the Metabase CLI for fast, hands-on analysis. MCP is useful for scoped lookups and summarized exports; the Metabase CLI's upload command loads CSV data into Metabase and creates a ready-to-query table and model.

Example workflow

• Ask the MCP server for a summarized slice of traces and spans for the apps and models you care about.
• Export the result as CSV, keeping stable IDs, apps, models, environments, token counts, costs, and timestamps.
• Run mb upload csv to load it into Metabase as a table and model, then build questions and dashboards on top.

Be honest about the limits

• MCP lookups are excellent for exploration, not scheduled reporting.
• A CSV upload is a snapshot; refresh it with mb upload replace or move to the pipeline for real history.
• Trace timestamps or daily rollups are required for latency and error-rate trends.
• mb upload csv needs an uploads database configured under Admin → Settings → Uploads.

How do you set up Arize Phoenix MCP and the Metabase CLI?

{
  "mcpServers": {
    "phoenix": {
      "command": "npx",
      "args": [
        "-y", "@arizeai/phoenix-mcp@latest",
        "--baseUrl", "https://your-phoenix.example.com",
        "--apiKey", "your-api-key"
      ]
    }
  }
}

Around 30 tools spanning projects, traces and spans, datasets, experiments, and prompt management — enough to pull scoped span summaries and experiment results without touching the database.

# Install the Metabase CLI
npm install -g @metabase/cli

# Log in (opens your browser; requires Metabase v62+)
mb auth login --url https://your-metabase.example.com

# Load a traces-and-spans export — creates a table AND a model
mb upload csv --file arize-phoenix-traces-and-spans.csv --collection root

# Refresh that same table later from a new export
mb upload replace <table-id> --file arize-phoenix-traces-and-spans.csv

Can you generate a Arize Phoenix dashboard with AI?

Yes. Use the prompt below with any assistant that can run the Phoenix MCP server and the Metabase CLI. It works end to end: if Arize Phoenix tables already exist in Metabase it analyzes those; otherwise it pulls scoped, summarized data, loads it with mb upload csv, then builds the dashboard and caveats any metric that needs missing history.

Create a polished Metabase dashboard for Arize Phoenix llm observability analytics.
Work end to end: get the data into Metabase if it isn't there yet, then build.

Goal: Help engineering, product, and finance partners understand traffic, latency, error rates, token usage, cost, and adoption from Arize Phoenix data.

Step 1 — Find or load the data:
- First, check what already exists in Metabase (search for arize-phoenix tables and
  models). If durable Arize Phoenix data is already present — synced from a warehouse
  or uploaded earlier — use it and skip to Step 2.
- If nothing is there, pull a scoped, summarized export with the Phoenix MCP server:
  traces and spans, plus experiments, datasets, annotations.
  Prefer aggregated or rollup views over raw traces. Write each result to a CSV,
  then load it with the Metabase CLI — run "mb upload csv --file <export>.csv" so
  each upload creates a table and a ready-to-query model. Use "mb upload replace
  <table-id> --file <export>.csv" to refresh an existing table instead of creating
  duplicates.

Step 2 — Inspect before querying:
Do not assume exact table or column names. Inspect available fields, apps, models,
environments, timestamps, and whether rollups or history exist before creating
duration or trend cards.

Important:
- Build on whatever data is present; don't claim Metabase connects natively to
  Arize Phoenix — it reads a database or CLI-uploaded tables.
- Never load raw prompt/response payloads into Metabase; use rollups, trace
  summaries, and experiment- or score-grain data.
- Only compute latency percentiles and durations when the required timestamps
  or pre-aggregated percentile fields exist.
- Exclude test, staging, and playground traffic from headline cost and quality
  cards, and segment by environment where the field exists.
- A single CSV is a point-in-time snapshot: only build trend cards if there is a
  usable date column or multiple periods have been uploaded.

Dashboard title: Arize Phoenix LLM Observability Overview

Sections:
1. Executive summary: Requests last 7 days; p95 latency; Error rate;
   Total cost last 30 days; Active users.
2. Traffic: Requests per day by app and environment; tokens per day.
3. Latency: p50/p95 by model by week; slowest ops or chains.
4. Errors: Error rate by model and app; failures by type; retries.
5. Cost and adoption: Cost by model; cost per request; active users of
   LLM features.

Filters: Date range, App, Model, Environment, User or team, Status.

Output: Build the dashboard if you have permission; otherwise provide the exact
questions, SQL, model definitions, and layout. Include caveats for any metric
that cannot be calculated from the available data.

How do you sync Arize Phoenix data into a database or warehouse?

For dashboards that need history and reliability, land Arize Phoenix rollups and metadata in a database first, then connect Metabase to that database.

Connector options

• Direct database or export pipeline — use the vendor's storage or export path when it reaches a database you control.
• Custom pipeline — use the Phoenix REST API for control over rollup grain, fields, and refresh cadence.
• MCP + CSV — use this for quick exploration and one-off slices.

Self-hosted Phoenix persists to PostgreSQL (recommended for production; SQLite is the default) — point Metabase at that same Postgres for direct SQL over spans, experiments, and annotations. Mind span retention settings, and land daily rollups in your warehouse if you need history beyond them.

Notes

• Decide the rollup grain first (daily per app/model is the workhorse) — it drives warehouse cost and every trend card.
• Land raw entity tables first, then build clean Metabase models on top.
• Normalize app, model, environment, status, duration, token-count, and window-start fields.
• Strip or hash prompt/response payloads and user identifiers before they reach the warehouse — cost and quality analytics don't need them.

How should you model Arize Phoenix data in Metabase?

Core tables

Modeling advice

• Build a clean llm_traces model with common columns across tools, so multi-source dashboards don't fork definitions.
• Separate entity tables (apps, models, datasets, prompts) from time-series rollups and trace- or score-grain tables.
• Exclude test, staging, and playground traffic from headline cost and quality metrics; keep environment as an explicit column.
• Use stable IDs for app, model, and experiment joins; display names and model aliases change.

Which Arize Phoenix metrics should you track in Metabase?

What SQL powers Arize Phoenix dashboards in Metabase?

These assume a cleaned analytical model in a warehouse (PostgreSQL dialect). Adjust table and column names to match your pipeline.

-- Keep p95 at the rollup grain it was computed. Do not MAX/AVG percentiles
-- across windows — that invents a fake weekly p95.
SELECT
  model,
  window_start,
  p95_latency_ms,
  requests
FROM llm_request_rollups
WHERE environment = 'production'
  AND window_start >= CURRENT_DATE - INTERVAL '30 days'
ORDER BY window_start, model;

SELECT
  app_name,
  date_trunc('week', window_start) AS week,
  SUM(requests) AS requests,
  SUM(error_count) AS errors,
  ROUND(
    100.0 * SUM(error_count) / NULLIF(SUM(requests), 0), 2
  ) AS error_rate_pct
FROM llm_request_rollups
WHERE environment = 'production'
GROUP BY app_name, 2
ORDER BY 2, error_rate_pct DESC;

SELECT
  date_trunc('day', started_at) AS day,
  app_name,
  COUNT(*) AS traces,
  SUM(total_tokens) AS total_tokens,
  ROUND(SUM(cost_usd), 2) AS cost_usd
FROM llm_traces
WHERE started_at >= CURRENT_DATE - INTERVAL '30 days'
GROUP BY 1, app_name
ORDER BY 1, cost_usd DESC;

What are common mistakes when analyzing Arize Phoenix in Metabase?

Related

Related analytics

Related dashboards

Related integrations

FAQ