MCP server · Analytics

csvglow MCP server

Turn a CSV or Excel file into an interactive HTML dashboard your AI can build for you.

csvglow is a small tool that takes a spreadsheet file and turns it into a single HTML dashboard page with charts and tables. Once you connect it to your AI assistant, you can just point at a file and ask for a dashboard. It is handy for anyone who has data in a CSV or Excel file and wants a quick visual overview without learning chart software.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app. Here, the helper is csvglow, and the skill is making dashboards from spreadsheet files. When you ask your AI to build a dashboard, it passes the file path to csvglow, and csvglow does the work.

What this MCP server does

You tell your AI which CSV or Excel file you want to look at. The AI passes that file path to csvglow. csvglow reads the file, figures out which columns are numbers, categories, or dates, and builds charts and a sortable table. It saves everything as one HTML file that opens in your browser. You get a finished dashboard page you can scroll through and share.

Flow diagram: you ask your AI “Make a dashboard from sales.csv”, on your own computer the csvglow MCP server works with your CSV or Excel file, and you get back A dashboard page you can open.

Click to zoom

What you can do with it

Turn a CSV file into an interactive HTML dashboard
Turn an Excel file into the same kind of dashboard
Get histograms and summary stats for numeric columns
Get bar charts for category columns
See a correlation heatmap between numeric columns
Get a sortable, filterable table of your rows
Save the dashboard to a file path you choose

Try asking your AI

“Make a dashboard from sales.csv”
“Turn report.xlsx into an HTML dashboard and save it as report.html”
“Build a dashboard from data.csv but don't open the browser”
“Create a dashboard from my quarterly numbers spreadsheet”

What it gives back to you

You get a single HTML file that opens in your browser as a dashboard. It shows charts like histograms, bar charts, time series, a correlation heatmap, and scatter plots, plus a sortable table of the first 1000 rows. There is also a short written findings section that points out things like top performers, underperformers, and possible contradictions across columns. In the chat, your AI usually tells you where the file was saved and what it found.

Before you start

What you need

A CSV, TSV, XLS, or XLSX file on your computer
Node.js installed if you use the npx option
Python with pip if you use the pip install option

Good to know

It reads the spreadsheet file you point it at, so only use files you are comfortable sharing with your AI assistant.

Install it with your AI

Add csvglow MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check csvglow MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.