Firebase logo

Dataki for Firebase

Ask Firebase in plain English

Ask Firebase Analytics and Crashlytics questions in plain English. Firebase's free BigQuery export puts active users, releases and crashes one question away.

Through BigQuery Firebase's BigQuery export. The guide takes about 5 minutes.

Follow the setup guide Open Dataki
app.dataki.ai / chat BigQuery · firebase_crashlytics

Which release crashed on the most devices this week?

Reading the schema, writing the query…
SQL 900 ms · 310 MB scanned 
SELECT application.display_version AS version,
       COUNT(DISTINCT installation_uuid) AS devices
FROM   firebase_crashlytics.com_acme_shop_ANDROID
WHERE  is_fatal
  AND  event_timestamp >= TIMESTAMP_TRUNC(CURRENT_TIMESTAMP(), WEEK)
GROUP BY version ORDER BY devices DESC LIMIT 5
Devices with a crash, by release This week · 5 rows
4.12.04.11.24.11.14.10.04.9.3 02004006008001k1.2k1.4k

4.12.0 crashed on 1,284 devices this week, nearly four times the release before it.

01Questions

What people ask Firebase

Each one becomes a query against the Firebase data, run read-only, with the SQL shown beside the chart so anyone who reads SQL can check it. Anything worth keeping goes on a dashboard that refreshes on its own.

  • Which release crashed on the most devices this week?
  • How many daily active users did each app version have?
  • What share of users on Android 14 hit a fatal crash?
  • How many users opened the app each day since the last release?

02From your assistant

Ask Firebase from Claude, ChatGPT or Cursor

Dataki runs a hosted MCP server. Add it to your assistant once and it can read the Firebase data in BigQuery and run read-only queries through Dataki. The assistant gets the rows back; the credentials stay encrypted in Dataki and never reach the model.

Setup for your assistant:

Claude · dataki (MCP) BigQuery · firebase_crashlytics

From the Crashlytics export, which issues affected the most users in the latest release?

  1. list_sources · finds BigQuery · firebase_crashlytics
  2. get_data_context · reads the tables and what the columns mean
  3. query · runs the SQL read-only, returns the rows
  4. render_ui · draws the chart from those rows, in the chat
server URL streamable http
https://dataki.ai/api/mcp

03Setting it up

Getting Firebase data to Dataki

Firebase's BigQuery export. The setup guide covers it step by step.

Setup
About 5 minutes. Analytics arrives within 24 hours; the first Crashlytics and Performance export can take up to 48.
Cost
Linking is free and works on the Spark plan, inside the BigQuery sandbox. Blaze adds full BigQuery and Crashlytics streaming.
History
From the day you link. Earlier data is not available for export.
You need
Owner or Firebase Admin on the project. Turning on Analytics export also needs Editor on the linked GA property.
Read the Firebase guide Open Dataki

The answer is still there tomorrow.

Ask in plain language. Dataki writes the SQL, runs it against your warehouse and draws the chart. Anything worth keeping becomes a dashboard with a link — not a message that scrolls away.

app.dataki.ai / chat

Which channels actually brought in revenue last quarter?

Queried bigquery · payments · 1.2 GB scanned 
SELECT channel,
       SUM(amount) AS revenue
FROM   payments
WHERE  created_at >= DATE_TRUNC(CURRENT_DATE(), QUARTER)
GROUP BY channel
ORDER BY revenue DESC

Revenue by channel

Q3 · 5 rows

Organic search
$412,900
Partner referral
$268,400
Email
$151,200
Paid social
$96,700
Direct
$61,300

One click later, that chart is a dashboard of its own:

app.dataki.ai/d/revenue-by-channel

Live, not a screenshot. It re-runs the query on a schedule, so the number your team reads on Friday is Friday's number.

  • Share the link with anyone. Viewers are free on every plan.
  • Edit the SQL by hand whenever the model gets the logic almost right.
  • Drop the same dashboard into your own product with one line of HTML.
Start free See how it works

Using Dataki with Firebase

Can I query Firebase in plain English instead of writing SQL?
Yes, once Firebase data is in BigQuery. Dataki has no Firebase connector of its own; it reads the dataset the data lands in (Firebase's BigQuery export), turns a plain-English question into SQL against it, runs it and returns a chart. The generated query is shown with every result, so you can verify or edit it.
How do I build a dashboard from Firebase data without an ETL pipeline?
Set up the route in the Firebase setup guide once. The copy into BigQuery then runs on its own, so there is no pipeline for you to maintain. Connect that dataset to Dataki, ask your question and keep the answer as a dashboard widget; Dataki queries the dataset at read time, so the dashboard is as fresh as the export.
Can Claude, ChatGPT or Cursor query my Firebase data?
Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect Firebase to Dataki, add that URL as a connector in Claude or ChatGPT (or in Cursor, VS Code or Claude Code with a Dataki key), and the assistant can read the schema and run read-only queries. It gets the rows back; the credentials stay encrypted in Dataki and are never handed to the model.