CSV, Excel, JSON, Parquet
Charts, histograms, heatmaps
Filter, merge, pivot, aggregate
CSV, Excel, charts as images
Creating visualizations with Claude
Data analysis in VS Code
Start your message with "Use stats compass to..." — this tells the AI to use Stats Compass tools instead of writing code or using shell commands.
Without this prefix, some AI clients may write Python code or use shell commands instead of the Stats Compass tools — especially for tasks like finding files on your machine.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"stats-compass": {
"command": "uvx",
"args": ["stats-compass-mcp"]
}
}
}
Add to your VS Code settings.json:
{
"mcp": {
"servers": {
"stats-compass": {
"command": "uvx",
"args": ["stats-compass-mcp"]
}
}
}
}
Run this command in your terminal:
claude mcp add stats-compass -- uvx stats-compass-mcp run
Start for free — locally or in the cloud. Upgrade when you need more.
Self-hosted on your machine
Cloud-hosted, no setup needed
For regular data work
No installation needed. Connect the hosted server directly from ChatGPT settings.
Enable developer mode
In ChatGPT, go to Settings → Apps → Advanced settings and enable developer mode.
Create a new app
Go back to Apps and select Create app. Fill in the form:
https://mcp.statscompass.io/mcpAuthorise and log in
Grant ChatGPT access to Stats Compass, then log in with Google or email. You'll be redirected back to ChatGPT automatically.
Start analysing
Upload a CSV and ask questions in plain English — "Summarise this dataset", "Run a regression to predict price", "Forecast the next 30 days".
Requires a ChatGPT paid account (Plus or above). Free tier includes 100 calls/month. See pricing.