MCP Analytics Suite

MCP server for data analytics — Shopify, Stripe, WooCommerce, eBay, CSV files, and more. Run statistical analysis, forecasting, and machine learning directly in Claude or Cursor. Ask a question, upload your data, get an interactive report.

> This is the public listing and documentation repository. Issues, feature requests, and examples live here. The API server code is maintained separately.

Sample Reports → • Try Demo → • Pricing →

<div align="center">

Every analysis starts with a question. We handle the rest.

🚀 Quick Start • 🔄 How It Works • 🛠️ MCP Tools • 🛡️ Security • 📖 Documentation

</div>

---

The Formula

<div align="center">
<h3>Question + Dataset = Analytics</h3>
<p>Transform business questions into actionable insights through intelligent discovery</p>
</div>

Overview

MCP Analytics Suite is an intelligent analytics platform that understands what you want to analyze and automatically selects the right approach. No statistics degree required — just describe your business question and let our AI-powered discovery handle the complexity.

Upload any CSV — Shopify orders, Stripe exports, WooCommerce reports, eBay data, ad platform reports, or any tabular data. Connect live data from Google Analytics 4 and Google Search Console via native connectors. Run regression, forecasting, clustering, A/B testing, customer LTV, churn prediction, and hundreds of other statistical methods. Get back interactive HTML reports with charts and AI-written insights.

Why MCP Analytics?

- Intelligent Discovery: Automatically finds the right analytical approach
- Complete Workflow: From question to insight in one seamless flow
- Zero Setup: Cloud-based processing, works instantly
- Enterprise Security: OAuth2, encryption, isolated processing
- Comprehensive Suite: Full range of analytical capabilities
- Interactive Reports: Shareable visualizations with AI insights

Quick Start

Installation

For Claude Desktop

Add to your config file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "mcp-analytics": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://api.mcpanalytics.ai/auth0"]
    }
  }
}

For Cursor

Add to .cursor/config.json in your project root:

{
  "mcpServers": {
    "mcp-analytics": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://api.mcpanalytics.ai/auth0"]
    }
  }
}

For VS Code (Continue Extension)

Add to your Continue config at ~/.continue/config.json:

{
  "models": [{
    "provider": "anthropic",
    "model": "claude-3-5-sonnet",
    "mcpServers": {
      "mcp-analytics": {
        "command": "npx",
        "args": ["-y", "mcp-remote@latest", "https://api.mcpanalytics.ai/auth0"]
      }
    }
  }]
}

For Claude Code

Add to claude_code_config.json:

{
  "mcpServers": {
    "mcp-analytics": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://api.mcpanalytics.ai/auth0"]
    }
  }
}

How It Works

The MCP Analytics Workflow

1. Ask Your Question - Describe what you want to analyze in natural language
2. Intelligent Discovery - tools.discover finds the right analytical approach
3. Data Upload - datasets.upload securely processes your data
4. Automated Analysis - tools.run executes with optimal configuration
5. Interactive Results - reports.view delivers shareable insights

User: "What drives our sales growth?"
MCP Analytics:
  → Discovers regression and correlation methods
  → Configures analysis for your data structure
  → Runs multiple analytical approaches
  → Returns comprehensive report with insights

MCP Tools

The platform provides a complete suite of MCP tools for end-to-end analytics:

Core Analytics Tools

- discover_tools - Natural language tool discovery (5-signal semantic search) - tools_run - Execute an analysis module on your data - tools_info - Get tool documentation and schema - tools_schema - Inspect column requirements for a tool

Data Management

- datasets_upload - Secure data upload with encryption - datasets_list - List your uploaded datasets - datasets_read - Preview dataset contents - datasets_download - Download a dataset - datasets_update - Update dataset metadata

Connectors

- connectors_list - List available data source connections - connectors_query - Pull live data from a connected source

Reporting & Insights

- reports_view - Open an interactive HTML report - reports_list - List your reports - reports_search - Semantic search across past analyses - agent_advisor - Conversational AI that guides analysis and interprets results

Platform Tools

- billing - Usage and subscription management - about - Platform information and status

Features

Natural Language Interface

Just describe what you need:

"What drives our revenue growth?"
"Find customer segments in our data"
"Forecast next quarter's sales"
"Did our marketing campaign work?"

Comprehensive Analysis Suite

<table>
<tr>
<td width="50%">

Statistical Methods
- Regression Analysis
- Advanced Modeling
- Hypothesis Testing
- Survival Analysis
- Bayesian Methods

</td>
<td width="50%">

Machine Learning
- Ensemble Methods
- Boosting Algorithms
- Neural Networks
- Clustering
- Dimensionality Reduction

</td>
</tr>
<tr>
<td width="50%">

Time Series
- Forecasting
- Seasonal Analysis
- Trend Detection
- Multivariate Models
- Causal Analysis

</td>
<td width="50%">

Business Analytics
- Customer Analytics
- Market Analysis
- Pricing Models
- Predictive Analytics
- Experimental Design

</td>
</tr>
</table>

Seamless Workflow

graph LR
    A[Ask in Claude/Cursor] --> B[MCP Analytics]
    B --> C[Secure Processing]
    C --> D[Interactive Report]
    D --> E[Share Results]

Example Usage

Basic Regression

User: "I have a CSV with house prices. Can you predict price based on size and location?"
Claude: [Runs linear regression, provides R², coefficients, and diagnostic plots]

Customer Segmentation

User: "Segment my customers in sales_data.csv into meaningful groups"
Claude: [Performs k-means clustering, creates segment profiles with visualizations]

Time Series Forecasting

User: "Forecast next quarter's revenue using our historical data"
Claude: [Applies ARIMA, generates predictions with confidence intervals]

Security & Compliance

Enterprise Security Features

- Authentication: OAuth2 via Auth0 with PKCE
- Encryption: TLS 1.3 for all data transfers
- Processing: Isolated Docker containers per analysis
- Data Handling: Ephemeral processing, no persistence
- Access Control: OAuth 2.0 scoped permissions with usage limits
- Audit Trail: Complete logging for compliance

Privacy & Data Handling

- Data Privacy: Ephemeral processing, no data retention
- User Rights: Data deletion upon request
- Secure Processing: Isolated containers per analysis
- Enterprise Options: Contact us for compliance requirements

Read full security documentation →

Architecture

flowchart TB
    subgraph "Client Integration"
        CLI[CLI/SDK]
        Claude[Claude Desktop]
        Cursor[Cursor IDE]
        MCP[MCP Protocol]
    end
subgraph "API Gateway"

        LB[Load Balancer]

        Auth[OAuth 2.0/Auth0]

        Rate[Rate Limiting]

    end
subgraph "Processing Layer"

        Router[Request Router]

        Queue[Job Queue]

        Workers[Processing Workers]

        Docker[Docker Containers]

    end
subgraph "Analytics Engine"

        Stats[Statistical Methods]

        ML[Machine Learning]

        TS[Time Series]

        Report[Report Generation]

    end
subgraph "Data Layer"

        Cache[Results Cache]

        Storage[Secure Storage]

        Encrypt[Encryption Layer]

    end
CLI --> LB

    Claude --> LB

    Cursor --> LB

    MCP --> LB
LB --> Auth

    Auth --> Rate

    Rate --> Router
Router --> Queue

    Queue --> Workers

    Workers --> Docker
Docker --> Stats

    Docker --> ML

    Docker --> TS
Stats --> Report

    ML --> Report

    TS --> Report
Report --> Cache

    Cache --> Storage

    Storage --> Encrypt
style Auth fill:#e8f5e9

    style Docker fill:#fff3e0

    style Report fill:#e3f2fd

Performance

- Dataset Size: Handles large datasets
- Processing Time: Fast cloud-based processing
- Secure Infrastructure: Isolated Docker containers
- API Access: RESTful API with authentication

Getting Started

Visit our website for pricing and signup →

Documentation

- Quick Start Guide - Get running in under a minute
- Architecture - How the platform works
- Connectors - GA4, GSC, and CSV data sources
- Pricing - Plans and limits
- Security - Security & compliance details
- API Reference - Complete API documentation
- Tutorials - Step-by-step guides

Support

- Issues: GitHub Issues
- Email: support@mcpanalytics.ai
- Docs: mcpanalytics.ai/docs
- Enterprise: sales@mcpanalytics.ai

Comparison with Other MCP Servers

| Feature | MCP Analytics | Google Analytics MCP | PostgreSQL MCP | Filesystem MCP |
|---------|--------------|---------------------|----------------|----------------|
| Use Case | Statistical Analysis | Web Metrics | Database Queries | File Access |
| Setup Time | 30 seconds | OAuth + Config | Connection string | Path config |
| Data Sources | Any CSV/JSON/URL | GA4 Only | PostgreSQL Only | Local files |
| Analysis Tools | Full Suite | GA4 Metrics | SQL Only | Read/Write |
| Machine Learning | ✅ Full Suite | ❌ | ❌ | ❌ |
| Visualizations | ✅ Interactive | ✅ Dashboards | ❌ | ❌ |
| Shareable Reports | ✅ | ❌ | ❌ | ❌ |

Detailed comparison →

About MCP Analytics

MCP Analytics is built by data scientists and engineers passionate about making advanced statistical analysis accessible through AI assistants. The platform runs validated, deterministic analysis modules — the same data and tool produce the same result every time, unlike LLM code generation.

Testing & Support

Testing Your Connection

After installation, restart your IDE and look for "MCP Analytics" in the available tools. On first use, you'll be prompted to authenticate via OAuth 2.0.

```bash