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

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

Is there a hosted Neon MCP server?

Dataki is one. Its remote MCP server reaches Neon through a read-only connection you set up once in Dataki, so nothing is installed on your machine and no connection string goes into an assistant's config. It offers tools to list sources, read the schema and its documented meaning, 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 Neon data without an ETL pipeline?

Connect Neon to Dataki with a read-only connection, ask your question, and keep the answer as a dashboard widget. Dataki queries Neon directly at read time, so there is no pipeline to build, no warehouse to sync into and no copy of your data to keep current.

Can Claude, ChatGPT or Cursor query my Neon data?

Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect Neon 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 Neon

Ask Neon in plain English

Connect your Neon Postgres database to Dataki and ask it questions in plain English. Dataki connects over TLS with a read-only role, and keeps the answers as live dashboards.

Connects directly A read-only Postgres role, over TLS.

Connect Neon Read the setup guide

app.dataki.ai / chat Neon · public

Which features did our 20 most active accounts use this week?

Reading the schema, writing the query…

WITH top AS (
  SELECT account_id FROM events
  WHERE  created_at >= DATE_TRUNC('week', NOW())
  GROUP BY account_id ORDER BY COUNT(*) DESC LIMIT 20)
SELECT feature, COUNT(*) AS uses
FROM   events JOIN top USING (account_id)
WHERE  created_at >= DATE_TRUNC('week', NOW())
GROUP BY feature ORDER BY uses DESC LIMIT 5;

Reports led with 4,812 uses across the 20 accounts, then invoicing with 3,406.

01Questions

What people ask Neon

Each one becomes a query against Neon, 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 features did our most active accounts use this week?
How many trials converted to paid in each of the last six months?
Which API keys made the most requests yesterday?
How long does it take a new account to create its first project, on average?

02From your assistant

Ask Neon from Claude, ChatGPT or Cursor

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

Setup for your assistant:

Claude · dataki (MCP) Neon · public

From our Neon database, show trial-to-paid conversion by month for this year.

list_sources · finds Neon · 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 Neon

A read-only Postgres role, over TLS. 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

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 Neon

Can I query Neon in plain English instead of writing SQL?: Yes. Dataki reads your Neon schema, turns a plain-English question into a query, runs it against Neon and returns a chart. The generated query is shown with every result, so you can verify or edit it.
Is there a hosted Neon MCP server?: Dataki is one. Its remote MCP server reaches Neon through a read-only connection you set up once in Dataki, so nothing is installed on your machine and no connection string goes into an assistant's config. It offers tools to list sources, read the schema and its documented meaning, 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 Neon data without an ETL pipeline?: Connect Neon to Dataki with a read-only connection, ask your question, and keep the answer as a dashboard widget. Dataki queries Neon directly at read time, so there is no pipeline to build, no warehouse to sync into and no copy of your data to keep current.
Can Claude, ChatGPT or Cursor query my Neon data?: Yes, through Dataki's hosted MCP server at https://dataki.ai/api/mcp. Connect Neon 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