Get Started with
MCP Analytics

Connect Claude to professional statistical analysis tools in 3 simple steps. Sign in with Google, GitHub, or email — no verification wait.

1

Install MCP Analytics - Choose Your Method

One-click installation or manual configuration - you choose!

📦 Prerequisites

Before installing MCP Analytics, ensure you have:

  • Node.js and npm installed - Required for the npx command
  • Node.js version 5.2 or higher (includes npx)

Download Node.js → or check if installed: node --version

🚀 Option A: One-Click Installation (Recommended)

Claude Desktop Extension (.mcpb)

  1. Download from mcpanalytics.ai/install
  2. Double-click the .mcpb file
  3. Click "Install" in Claude Desktop
  4. Complete Auth0 authentication

Platform-Specific Installers

  • 🪟 Windows: PowerShell installer
  • 🍎 macOS: Shell script installer
  • 🐧 Linux: Bash installer
  • 📝 VS Code: Marketplace extension

Visit install page for all options

⚙️ Option B: Manual Configuration

For advanced users - add to Claude Desktop config:

Location: Settings → Developer → Edit Config

claude_desktop_config.json
// Manual config option - or use one-click installer above! { "mcpServers": { "mcpanalytics": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://api.mcpanalytics.ai/auth0" ] } } }
✓ Configuration ready - save and restart Claude Desktop
2

Authenticate with Auth0

Complete the secure Auth0 login in your browser

What happens:

When you restart Claude Desktop, Auth0 will open in your browser for secure authentication:

  • Browser opens automatically - Auth0 secure login page
  • Sign in or create account - use Google, GitHub, or email
  • Instant activation - no email verification needed
  • MCP connection established - tools available immediately
  • Tokens managed automatically - secure OAuth2 flow

Check connection status:

Type /mcp in Claude to see server status and available tools

Claude Desktop
⏺ Checking MCP server status...
mcpanalytics - about
(MCP)(topic: "platform")
{
"company": "PeopleDrivenAI",
"description": "Enterprise AI-powered statistical analysis platform",
... +48 lines (ctrl+r to expand)
}
mcpanalytics - discover.tools
(MCP)(query: "list available tools", limit: 10)
[
"linear_regression",
"ridge_regression",
"lasso_regression",
"arima",
"correlation",
"t_test",
"anova",
"chi_square",
"pca",
"time_series_forecast"
]
✓ Comprehensive statistical toolkit available via MCP
3

Run Your First Analysis

Start analyzing data with natural language requests

How it works:

With Auth0 authentication complete, you get 10 free tasks on the Demo plan. Here are the ways to get data into your analysis:

📦 Option 1: Demo Datasets (Quickest)

3 pre-loaded datasets are available immediately on signup:

  • Advertising Spend - Marketing spend vs. sales across channels
  • Survey Responses - Categorical survey data with demographics
  • Retail Demand - Daily sales for time series forecasting

Ask Claude to list your datasets or just say "run a demo analysis" to get started.

🔗 Option 2: Connect Live Data Sources

Pull data directly from platforms you already use:

  • Google Analytics 4 - Traffic, engagement, and conversion data
  • Google Search Console - Search performance, clicks, and rankings

Use connectors_list to see available connections. No file download needed.

📤 Option 3: Upload Your Own Data

Secure upload with AES-256 encryption:

  • Generate upload token with datasets.upload
  • Upload CSV, TSV, or JSON via cURL
  • Access with uuid://dataset_id:your_secret

Example walkthrough:

Let's run an analysis using a demo dataset and see what you get back.

▶ You
I want to see how my advertising spend relates to sales. Can you run a regression on my demo data?
⚬ Claude
Sure! I'll use your Advertising Spend demo dataset to run a linear regression and see which channels drive the most sales.
⏺ Claude
mcpanalytics - tools_run
(MCP)(
tool_name: "demo__advertising__marketing_spend__linear_regression",
dataset: "demo://advertising",
generate_insights: true
)
✅ SUCCESS: tools_run
📊 Interactive Visual Report Available!
https://app.mcpanalytics.ai/report/rpt_AdSpend_Regression
Model Results:
• R² Score: 0.897 (89.7% variance explained)
• Top Channel: TikTok ($4.20 return per $1 spent)
• Significant Predictors: 3 of 3
... +300 lines available in report
⚬ Claude
The analysis is complete. Here is your interactive report: Key findings from the advertising spend analysis:
• Model Quality: R² = 0.897 (89.7% variance explained)
• TikTok: Highest ROI at $4.20 return per $1 spent
• Facebook: Significant but diminishing returns above $50K
• Google Ads: Steady baseline contributor to revenue

What you can do with your report:
• Card viewer - Browse results card by card with an AI insights panel
• PDF export - One-click download with charts on each page
• Share - Send a token link to colleagues (no login required to view)

You're ready to go!

Your Demo plan includes free tasks across all analytical tools. Explore what MCP Analytics can do:

Browse Sample Reports View Pricing Open Dashboard