Dataki for ChatGPT

Connect ChatGPT to your database

Add Dataki as a connector in ChatGPT, sign in once, and ChatGPT can query the sources you have connected to Dataki. It writes the SQL; Dataki runs it read-only on its own side and returns the rows. Your database password never reaches OpenAI.

  1. ChatGPT
  2. Dataki MCP server
  3. Your database, read-only
Signs in with
Sign in with OAuth. No key to copy.
Works in
Any ChatGPT conversation where the Dataki connector is switched on.
You need
A ChatGPT Plus, Pro, Business or Enterprise plan, and a Dataki account with at least one data source.
Server URL
https://dataki.ai/api/mcp

01Set it up

4 steps, a couple of minutes

Dataki's connect page walks through the same steps with buttons, and creates a key wherever one is needed.

  1. 01

    Turn on developer mode

    In ChatGPT, open Settings → Apps & Connectors → Advanced settings and turn on Developer mode. ChatGPT adds custom MCP connectors from there.

  2. 02

    Create the connector

    Back in Apps & Connectors, click Create. Name it Dataki, paste the URL below and choose OAuth.

    Remote MCP server URL
    https://dataki.ai/api/mcp
  3. 03

    Sign in to Dataki when ChatGPT asks

    Approve what ChatGPT may reach. It gets its own credential, bound to your Dataki account, which you can revoke from Dataki.

  4. 04

    Ask it something

    Start with What data can you see in Dataki?, then ask about the data itself.

02Ask it

What to ask in a ChatGPT conversation with the Dataki connector on

The assistant finds your sources, reads what the columns mean, writes the SQL and hands it to Dataki, which runs it read-only and returns the rows. The query is part of every answer.

How did revenue move each month this year, and which plans carried it?

Dataki runs the query against your warehouse and draws the chart from the rows that came back, not from numbers the model typed.

Which customers upgraded this quarter, and what did each one add?

Answered with a table as well as a sentence, so the figures can be checked line by line.

Save these two charts to a dashboard called Weekly review and share it with the team.

The dashboard lives in Dataki on a permanent link. It refreshes on its own; nobody has to ask again next week.

Tell me when daily orders fall below 100.

watch_metric runs the query on a schedule and emails an alert when the number crosses the line you set. list_schedules shows what is already being watched.

04Worth knowing

What ChatGPT gets, and what it never does

Why it needs a paid plan
Custom connectors are added in ChatGPT's developer mode, which is available on the Plus, Pro, Business and Enterprise plans. On a free ChatGPT account, use Dataki in the browser instead: it answers the same questions directly.
It acts as you, and only as you
The connector holds no credential of its own. Anything you cannot reach in Dataki, ChatGPT cannot reach either, and team restrictions, spend ceilings and the query log all still apply.
What ChatGPT receives
Query results: the rows each query returned, and your schema when it asks for it. Never a host name, a user or a password.

More on the server itself, and every tool it offers, on the MCP server page. How credentials, keys and the query log work: security and governance.

Dataki and ChatGPT

Can ChatGPT connect to my SQL database?
Yes, through a remote MCP connector. Connect your database to Dataki with a read-only user, then add https://dataki.ai/api/mcp as a connector in ChatGPT's developer mode and sign in. ChatGPT can then read the schema and run read-only queries through Dataki, which returns the rows.
Which ChatGPT plans can use the Dataki connector?
Plus, Pro, Business and Enterprise. Custom connectors are added in developer mode, under Settings → Apps & Connectors → Advanced settings.
Does ChatGPT get my database password?
No. Your database credentials are stored encrypted in Dataki and are never sent to ChatGPT or to any model. ChatGPT calls Dataki's MCP server, the server runs the SQL on its side with a read-only role, and only the rows that come back reach the conversation.
Can ChatGPT change or delete data through Dataki?
No. Dataki's query tool is read-only: a statement that changes data is refused before it runs, and the database connection itself uses a role that cannot write. ChatGPT can create and edit Dataki dashboards, which are Dataki's own records, never rows in your database.
Which databases can ChatGPT query through Dataki?
Any source connected to Dataki: Google BigQuery, PostgreSQL, MySQL, Amazon Redshift, Supabase, Google Sheets and uploaded CSV or Excel files, including hosted databases such as Neon, Amazon RDS, Cloud SQL and PlanetScale. Google Analytics 4, Firebase, Search Console, Firestore and Stripe work through their exports to BigQuery. One question can read more than one source.

Connect ChatGPT. Ask it something.

Connect a source to Dataki, add the server to ChatGPT, and the first answer is one question away. Anything worth keeping becomes a dashboard with a link that stays live.