CSV and Excel files logo

Dataki for CSV and Excel files

Ask CSV and Excel files in plain English

Upload a CSV or Excel file and ask it questions in plain English. Dataki loads each sheet as a table, answers with SQL and a chart, and keeps what matters as a dashboard.

Connects directly Upload; each sheet becomes a table.

Connect CSV and Excel files
app.dataki.ai / chat sales.xlsx · 3 sheets

What were total sales each month in this file, and which month grew fastest?

Reading the schema, writing the query…
SQL 60 ms · read-only 
SELECT DATE_TRUNC('month', order_date) AS month, SUM(total) AS sales
FROM   sales.orders
GROUP BY month
ORDER BY month
Sales by month 8 rows
JanFebMarAprMayJunJulAug $0$50K$100K$150K

July grew fastest: $121K in sales, up 23% on June.

01Questions

What people ask CSV and Excel files

Each one becomes a query against CSV and Excel files, 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.

  • What were total sales by month, and which month grew fastest?
  • Which customers appear in both sheets?
  • What is the median order value per region?
  • Which rows have a negative quantity?

02From your assistant

Ask CSV and Excel files from Claude, ChatGPT or Cursor

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

Setup for your assistant:

Claude · dataki (MCP) sales.xlsx · 3 sheets

Using the sales file I uploaded to Dataki, chart revenue by month and region.

  1. list_sources · finds sales.xlsx · 3 sheets
  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

Connecting CSV and Excel files

Upload; each sheet becomes a table.

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/sales-by-month sales.xlsx · 3 sheets

3 views · Updated just now

Sales by month 8 rows
JanFebMarAprMayJunJulAug $0$50K$100K$150K

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

app.dataki.ai/dashboards/sales-by-month

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 CSV and Excel files

Can I ask questions about a CSV or Excel file in plain English?
Yes. Upload the file to Dataki and it loads each sheet as a table, turns a plain-English question into SQL, runs it and returns a chart. The generated query is shown with every result, so you can verify or edit it.
Does Dataki keep the data from an uploaded file up to date?
No. An uploaded file is a snapshot: Dataki answers from the copy you uploaded. For data that changes, connect the source it comes from, or keep it in a Google Sheet, which Dataki reads live.
Can an AI assistant like Claude or Cursor query a file I uploaded?
Yes. Dataki's MCP server lets any Model Context Protocol client query the sources you have in Dataki, uploaded files included. The assistant gets results back, never the file itself.