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.

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…

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

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?

list_sources · finds BigQuery · firebase_crashlytics
get_data_context · reads the tables and what the columns mean
query · runs the SQL read-only, returns the rows
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

After the chat

The answer is still there tomorrow.

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

app.dataki.ai/dashboards/devices-with-a-crash-by-release BigQuery · firebase_crashlytics

3 views · Updated just now

One click on the answer, and that chart is a dashboard of its own:

app.dataki.ai/dashboards/devices-with-a-crash-by-release

Live, not a screenshot. It runs the query again whenever it is opened, so the number your team reads on Friday is Friday's number.

Share it: Send the link to anyone. People who only look are free on every plan.
Fix it: Edit the SQL by hand whenever the model gets the logic almost right.
Embed it: Put the same dashboard in your own product with two HTML tags.

Start free More on dashboards

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.

Product

Solutions

Resources