Can I query PostgreSQL in plain English instead of writing SQL?

Yes. Dataki reads your PostgreSQL schema, turns a plain-English question into a query, runs it on PostgreSQL and returns a chart. The query is shown with every result, so you can check or edit it.

Is there a hosted PostgreSQL MCP server?

Yes, Dataki. Its remote MCP server reaches PostgreSQL through a read-only connection you set up once in Dataki: nothing to install, and no connection string in your assistant's config. Assistants can list sources, read the schema and what it means, run read-only SQL, draw charts in the conversation and save dashboards. Every query is logged with the key that ran it.

How do I build a dashboard from PostgreSQL data without an ETL pipeline?

Connect PostgreSQL to Dataki with a read-only connection, ask your question and save the answer as a dashboard widget. Dataki queries PostgreSQL live, so there is no pipeline to build, no warehouse to sync and no copy of your data to maintain.

Can Claude, ChatGPT or Cursor query my PostgreSQL data?

Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect PostgreSQL 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 your assistant can read the schema and run read-only queries. It works with the results, while your credentials stay encrypted in Dataki and never reach the model.

Dataki for PostgreSQL

Ask PostgreSQL in plain English

Ask your PostgreSQL database questions in plain English. Dataki writes the SQL, runs it with a read-only user and charts the answer — in the browser, or from Claude, ChatGPT or Cursor.

Connects directly A read-only user, over TLS, from one fixed IP.

Connect PostgreSQL Read the setup guide

app.dataki.ai / chat PostgreSQL · public

Which plans brought in the most new revenue this quarter?

Reading the schema, writing the query…

SELECT p.name AS plan, SUM(s.amount) AS new_revenue
FROM   subscriptions s
JOIN   plans p ON p.id = s.plan_id
WHERE  s.started_at >= DATE_TRUNC('quarter', NOW())
GROUP BY p.name ORDER BY new_revenue DESC;

Business annual brought in $184K of the quarter's $455K in new revenue, 40% of it.

01Questions

What people ask PostgreSQL

Each one becomes a query against PostgreSQL, 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.

How many accounts signed up each week this quarter, and how many are still active?
Which customers have the most open orders, and how old is the oldest one?
What share of revenue came from annual plans last month?
Which tables reference the users table, and how are they joined?

02From your assistant

Ask PostgreSQL from Claude, ChatGPT or Cursor

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

Setup for your assistant:

Claude · dataki (MCP) PostgreSQL · public

Chart weekly signups from the users table for this year and save it to a dashboard called Growth.

list_sources · finds PostgreSQL · public
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

Connecting PostgreSQL

A read-only user, over TLS, from one fixed IP. The setup guide covers it step by step.

Setup: About 5 minutes.
Connects from: 34.89.253.13, one fixed address to allow.
Encryption: TLS whenever the server offers it, which most hosts require. The server certificate is not verified, and client certificates are not supported.
What it reads: Tables and views in the public schema.

Read the Hosted PostgreSQL guide Open Dataki

Live dashboards

Every answer can become a live dashboard.

Ask in plain English. Dataki writes the SQL, runs it on your database and charts the answer. Keep it as a dashboard with its own link, and your team sees current numbers every time they open it.

app.dataki.ai/dashboards/new-revenue-by-plan PostgreSQL · public

3 views · Updated just now

One click turns the answer into a dashboard:

app.dataki.ai/dashboards/new-revenue-by-plan

Always current. The query runs again whenever the dashboard opens, so Friday's meeting sees Friday's numbers.

Share it: Send the link to anyone. Viewers are free on every plan.
Refine it: The SQL is always visible. Adjust it by hand or ask for a change.
Embed it: Put the same dashboard in your own product with two HTML tags.

Start free More on dashboards

Using Dataki with PostgreSQL

Can I query PostgreSQL in plain English instead of writing SQL?: Yes. Dataki reads your PostgreSQL schema, turns a plain-English question into a query, runs it on PostgreSQL and returns a chart. The query is shown with every result, so you can check or edit it.
Is there a hosted PostgreSQL MCP server?: Yes, Dataki. Its remote MCP server reaches PostgreSQL through a read-only connection you set up once in Dataki: nothing to install, and no connection string in your assistant's config. Assistants can list sources, read the schema and what it means, run read-only SQL, draw charts in the conversation and save dashboards. Every query is logged with the key that ran it.
How do I build a dashboard from PostgreSQL data without an ETL pipeline?: Connect PostgreSQL to Dataki with a read-only connection, ask your question and save the answer as a dashboard widget. Dataki queries PostgreSQL live, so there is no pipeline to build, no warehouse to sync and no copy of your data to maintain.
Can Claude, ChatGPT or Cursor query my PostgreSQL data?: Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect PostgreSQL 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 your assistant can read the schema and run read-only queries. It works with the results, while your credentials stay encrypted in Dataki and never reach the model.

Product

Solutions

Resources