Stats Compass - VS Code Extension

A VS Code extension that provides the Stats Compass MCP server for AI assistants.

What is Stats Compass?

Stats Compass provides 50+ pandas-powered tools for data science workflows:

Data Loading: Load CSV, Excel, and sample datasets
Cleaning: Drop nulls, impute, dedupe, handle outliers
Transforms: Filter, groupby, pivot, encode, scale
EDA: Describe, correlations, hypothesis tests, data quality
Visualization: Histograms, scatter, bar, ROC curves, confusion matrix
ML Workflows: Classification, regression, time series forecasting

Requirements

VS Code 1.101+
GitHub Copilot (or another AI assistant that supports MCP)

No Python installation or additional setup needed — the extension connects to the Stats Compass cloud server.

Installation

Install from the VS Code Marketplace
The extension will automatically register the Stats Compass MCP server
Sign in when prompted (free tier includes 50 tool calls/month)
Use with GitHub Copilot or other AI assistants that support MCP

Want to run locally instead?

If you prefer a fully local setup, install via pip/uvx and configure MCP manually. See the Stats Compass MCP Server repo for instructions.

Usage

Once installed, AI assistants can use Stats Compass tools to:

Load and explore your data files
Clean and transform datasets
Create visualizations
Train ML models

Start your message with "Use stats compass to..." for best results. This tells the AI to use the Stats Compass tools rather than writing code or using other methods.

Example prompts:

"Use stats compass to load ~/Downloads/sales.csv and show me a summary"
"Use stats compass to find my CSV files in Downloads"
"Use stats compass to run EDA on the dataset"
"Use stats compass to create a histogram of the price column"
"Use stats compass to test if there's a significant difference in scores between group A and B"
"Use stats compass to train a classification model to predict churn"

License

MIT

Stats Compass MCP Server

Inference Labs