How Can We Help?

Add the MCP Analytics server to your Claude Desktop configuration:

1. Open Claude Desktop Settings → Developer → Edit Config

2. Add our server configuration with npx -y mcp-remote@latest https://api.mcpanalytics.ai/auth0

3. Restart Claude Desktop and authenticate with Auth0

4. Type /mcp to verify the connection

MCP Analytics provides a comprehensive suite of professional statistical tools including:

• Multiple regression techniques (Linear, Ridge, Lasso, and more)

• Advanced time series forecasting (ARIMA, Prophet, and beyond)

• Exploratory analysis (Correlation, PCA, clustering)

• Hypothesis testing (T-Test, ANOVA, Chi-Square, and others)

• Causal inference and Bayesian methods

• Customer analytics and segmentation tools

All tools include interactive visualizations and AI-generated insights.

You have three options for providing data:

1. Public URLs: Use CSV files from GitHub directly

2. Test Datasets: Use our pre-loaded datasets with provided UUIDs

3. Upload Your Own: Ask Claude to generate an upload token, then use cURL to upload your file with encryption

Yes, we take data security seriously:

• End-to-end encryption with your secret key

• Data automatically deleted after 30 days

• Secure Auth0 authentication

• Isolated Docker execution environments

• HTTPS for all data transmission

The 24-hour demo includes:

• 100 free analyses

• Access to all 10 statistical tools

• Interactive reports with visualizations

• AI-generated insights

• Test datasets for experimentation

If you're experiencing connection issues, clear the MCP cache:

rm -rf ~/.mcp-auth ~/.mcp-remote

Then restart Claude Desktop and reconnect to MCP Analytics.

Yes! All reports generate shareable URLs that:

• Work without authentication

• Include interactive visualizations

• Contain full analysis results

• Can be accessed for 7-30 days (depending on your plan)

MCP Analytics supports multiple data formats:

• CSV (comma-separated values)

• TSV (tab-separated values)

• Excel (.xlsx, .xls)

• JSON (JavaScript Object Notation)

• Parquet (columnar storage)

• Feather (fast binary format)