# MCP Analytics Suite

**The statistical analyst in your AI chat.** Bring a CSV (or connect a live source) and a question. A standing team of specialist agents builds a custom analysis specific to your data, validates the methodology, and ships back a citable, interactive report. The analysis is **yours** — it lives in your library, reruns on fresh data for a fraction of the creation cost, and is queryable from Claude, Cursor, or any MCP client. The work compounds.

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

[Sample Reports →](https://mcpanalytics.ai/case-studies) • [Try Demo →](https://mcpanalytics.ai/demo) • [Pricing →](https://mcpanalytics.ai/pricing)

**Try it before installing anything.** The [free tools](https://mcpanalytics.ai/free/) run in the browser on a CSV you upload — no account, no key, no MCP client. Each one is a real analysis with the method written out: [PCA](https://mcpanalytics.ai/free/standard_pca), [correlation](https://mcpanalytics.ai/free/standard_correlation), [forecasting](https://mcpanalytics.ai/free/standard_forecasting), [RFM segmentation](https://mcpanalytics.ai/free/standard_rfm), [regression (GLM)](https://mcpanalytics.ai/free/standard_glm).

<div align="center">

[![Glama Score](https://glama.ai/mcp/servers/embeddedlayers/mcp-analytics/badges/score.svg)](https://glama.ai/mcp/servers/embeddedlayers/mcp-analytics)
[![npm](https://img.shields.io/npm/v/@mcp-analytics/mcp-analytics)](https://www.npmjs.com/package/@mcp-analytics/mcp-analytics)
[![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)
[![Platform](https://img.shields.io/badge/Platform-MCP_Compatible-blue)](https://mcpanalytics.ai/install)
[![Docs](https://img.shields.io/badge/Docs-mcpanalytics.ai-brightgreen)](https://mcpanalytics.ai/docs)

**Hire the team. Own the analysis. Rerun forever.**

[🚀 Quick Start](#quick-start) • [🔄 How It Works](#how-it-works) • [🛠️ MCP Tools](#mcp-tools) • [🛡️ Security](#security--compliance) • [📖 Documentation](#documentation)

</div>

<div align="center">

[![Demo Video](assets/demo-preview.png)](https://github.com/embeddedlayers/mcp-analytics/releases/download/v1.0.4/demo.mp4)

*Click to watch: Ask a question → upload data → get an interactive report with AI insights*

</div>

---

## Overview

You bring data and a question. A pipeline of specialist agents — spec drafter, builder, verifier, fixer, deployer — turns your question into a custom analysis for your data. The result is an interactive report: charts, AI-narrated insights, exportable PDF, embedded source code, citable. Every commissioned analysis joins your private library — query it from any MCP client, rerun on fresh data with one call, share with collaborators on your terms.

**Cornerstone modules** ship pre-built (t-tests, regression, churn, segmentation, forecasting, customer LTV, A/B testing, time series, survival analysis, and more) so you can see a finished report in under a minute and verify the team can build things that work. **Custom analysis creation** is the named revenue event — pay once to build the capability, own it, rerun for a fraction of the creation price. A build that fails is never billed.

Connect data however it lives: CSV upload, public URL, or live OAuth connectors for Google Analytics 4 and Google Search Console (more coming). Once a connector is linked, every rerun pulls fresh data automatically — no re-export step.

### Choose Your Depth — Four Tiers

Every analysis runs through the same pipeline — you choose how far it goes:

| Tier | What you get | Time |
|------|-------------|------|
| **Snapshot** | One chart and a verified insight — an instant read of your data, covered by your welcome credits | ~2 min |
| **JSON** | One computed statistical answer — the numbers and the method — deployed as a tool you re-run on fresh data | ~5 min |
| **Brief** | The computed answer, presented — chart, key figures, and method on a single shareable page | ~7 min |
| **Deck** | The full study — a complete statistical report built to your brief and independently verified; a durable module you own and re-run forever | 30–45 min |

More rigor outranks more charts: going deeper buys real statistical methods — hypothesis tests, regression, diagnostics — not just more cards. You pay for depth, and only if the build succeeds. [How the tiers work →](https://mcpanalytics.ai/tiers)

### Why MCP Analytics

- **Citable** — APA / MLA / Chicago / BibTeX in one click, ready for papers, decks, and regulatory filings
- **Sourceable** — R source code embedded in every report; a skeptical reader can run it and get the same answer
- **Reproducible** — fixed seeds, Docker isolation, named methods; same input → same output, forever
- **Yours** — every commissioned module is private to your account; rerun on fresh data, query across your portfolio
- **MCP-native** — query the library from Claude, Cursor, Windsurf, or any MCP client
- **Secure** — OAuth2, encryption at rest, isolated container processing per analysis
- **Honest** — when an analysis has issues, the team gives you a free re-run; the relationship is built on the report being right

## Quick Start

### 1. Get an API Key

Sign up free at [account.mcpanalytics.ai](https://account.mcpanalytics.ai), go to account settings, and copy your API key (starts with `mcp_`). You get **9,000 welcome credits**, no credit card required. That covers about seven full analyses at any depth, plus re-runs.

### 2. Connect

Three options — all connect to the same platform with the same tools.

#### Option A: npx Install (Recommended)

Works with Claude Desktop, Cursor, Windsurf, and any stdio MCP client. Requires Node.js 18+.

**Claude Desktop** — add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):

```json
{
  "mcpServers": {
    "mcpanalytics": {
      "command": "npx",
      "args": ["-y", "@mcp-analytics/mcp-analytics"],
      "env": {
        "MCP_ANALYTICS_API_KEY": "mcp_your_key_here"
      }
    }
  }
}
```

**Cursor / Windsurf** — add to `.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "mcpanalytics": {
      "command": "npx",
      "args": ["-y", "@mcp-analytics/mcp-analytics"],
      "env": {
        "MCP_ANALYTICS_API_KEY": "mcp_your_key_here"
      }
    }
  }
}
```

**Claude Code** — run in your terminal:

```bash
claude mcp add mcpanalytics -- npx -y @mcp-analytics/mcp-analytics
# Then set MCP_ANALYTICS_API_KEY in your environment
```

#### Option B: Direct API Key (No npm)

For MCP clients that support Streamable HTTP transport with custom headers:

```json
{
  "mcpServers": {
    "mcpanalytics": {
      "url": "https://api.mcpanalytics.ai/mcp/api-key",
      "headers": {
        "X-API-Key": "mcp_your_key_here"
      }
    }
  }
}
```

#### Option C: OAuth2 (No API Key)

Zero-config — a browser opens for login on first connection:

```json
{
  "mcpServers": {
    "mcpanalytics": {
      "url": "https://api.mcpanalytics.ai/auth0"
    }
  }
}
```

#### Browse Tools First (No Account Needed)

Explore the full tool catalog before signing up:

```bash
# Static metadata (tool names, descriptions, all transport options)
curl https://api.mcpanalytics.ai/.well-known/mcp.json

# MCP protocol discovery (no auth — works with any MCP client)
curl -X POST https://api.mcpanalytics.ai/mcp/discover \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1,"params":{}}'
```

### 3. Start Analyzing

Restart your MCP client. Ask:

- *"Upload sales.csv and find what drives revenue"*
- *"What statistical test should I use for this survey data?"*
- *"Forecast next quarter's sales from this time series"*

## How It Works

### The MCP Analytics Workflow

1. **Upload your data** — `datasets_upload` securely processes your CSV (or reuse an existing dataset / connected source)
2. **Commission the analysis** — `create_analysis` takes your question in plain language, your dataset, and the tier you choose (snapshot, json, brief, or deck)
3. **Watch it build** — `build_status` reports progress, queue position, and the report link when done
4. **Get the report** — `reports_view` delivers the interactive report; `report_cards` displays individual cards inline
5. **Rerun forever** — `run_analysis` re-runs any analysis you own on fresh data for a fraction of the creation cost

```
User: "What drives our sales growth?"
MCP Analytics:
  → Scopes the right statistical method for your data's shape
  → Writes R in an isolated container — deterministic, fixed seeds
  → Runs it, then independently verifies numbers and narrative
  → Returns a citable, interactive report you own
```

## MCP Tools

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

### Analysis
- **`create_analysis`** - Commission a new analysis from a plain-language question, at the tier you choose
- **`build_status`** - Track a build: stage progress, queue position, report link
- **`run_analysis`** - Run an analysis you own (or one discovered via `discover_tools`) on fresh data
- **`modify_analysis`** - Turn an existing analysis into a new version — reword the question, change the framing

### Discovery
- **`discover_tools`** - Browse what you can run: your commissioned analyses plus the prebuilt library
- **`tools_schema`** - Get an analysis's parameter schema — always call this before `run_analysis`

### Data Management
- **`datasets_upload`** - Secure data upload with encryption
- **`datasets_list`** - List and search your uploaded datasets

### Connectors
- **`connectors_list`** - List available data source connections
- **`connectors_query`** - Pull live data from a connected source

### Reporting & Insights
- **`reports_view`** - Get a shareable browser link for a report
- **`reports_list`** - Your report library — every analysis delivered, searchable in plain language
- **`report_cards`** - Browse a delivered report's individual cards (charts, tables, insights)
- **`ask_library`** - Ask one question across *all* your delivered analyses; get a synthesized answer with citations back to each source report
- **`agent_advisor`** - AI help desk — which analysis fits your question, and how to read the result

### Platform Tools
- **`billing`** - Usage and credit management
- **`account_link`** - Link to the right account page for anything not doable in chat
- **`about`** - Platform documentation and info — how it works, tiers, usage

> Browse the catalog yourself, without an account:
> `curl -X POST https://api.mcpanalytics.ai/mcp/discover -H 'Content-Type: application/json' -d '{"jsonrpc":"2.0","method":"tools/list","id":1,"params":{}}'`
> Discovery returns the 15 tools that work pre-auth; `billing`, `connectors_list`,
> and `connectors_query` appear once you connect with a key or via OAuth.

## 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

```mermaid
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 →**](SECURITY.md)

## Architecture

```mermaid
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 →**](https://mcpanalytics.ai)

## Documentation

- [**Quick Start Guide**](docs/quickstart.md) - Get running in under a minute
- [**Architecture**](docs/ARCHITECTURE.md) - How the platform works
- [**Connectors**](docs/connectors.md) - GA4, GSC, and CSV data sources
- [**Pricing**](docs/pricing.md) - Credits, tiers, and plans
- [**How Credits Work**](https://mcpanalytics.ai/how-credits-work) - The credit model explained
- [**Security**](SECURITY.md) - Security & compliance details
- [**Tutorials**](https://mcpanalytics.ai/tutorials) - Step-by-step guides

## Support

- **Issues**: [GitHub Issues](https://github.com/embeddedlayers/mcp-analytics/issues)
- **Email**: support@mcpanalytics.ai
- **Docs**: [mcpanalytics.ai/docs](https://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 →**](https://mcpanalytics.ai/compare)

## 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 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 MCP client and look for "MCP Analytics" in the available tools. You should see tools like `create_analysis`, `discover_tools`, `datasets_upload`, etc.

```bash
# Test the stdio proxy directly:
MCP_ANALYTICS_API_KEY=mcp_your_key npx -y @mcp-analytics/mcp-analytics
# Should output a "[mcp-analytics] Connected to https://api.mcpanalytics.ai" line with the tool count
```

### Troubleshooting

If MCP Analytics doesn't appear after installation:
1. Ensure your config file is valid JSON
2. Restart your MCP client completely
3. Verify your API key starts with `mcp_`
4. Check the client's developer console for errors
5. Try running the npx command in a terminal to see errors

For support: support@mcpanalytics.ai

## Contributing

While the core server is proprietary, we welcome contributions to:

- Documentation improvements
- Example notebooks and use cases
- Bug reports and feature requests
- Community tools and integrations

See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

## License

Copyright © 2026 PeopleDrivenAI LLC. All Rights Reserved.

MCP Analytics is a product of PeopleDrivenAI LLC.

This is commercial software. Use of the MCP Analytics service is subject to our:
- [Terms of Service](https://mcpanalytics.ai/terms)
- [Privacy Policy](https://mcpanalytics.ai/privacy)

---

<div align="center">

**Ready to transform your data analysis workflow?**

[**Get Started Free**](https://mcpanalytics.ai/signup) | [**Read Docs**](https://mcpanalytics.ai/docs) | [**View Demo**](https://mcpanalytics.ai/demo)

Built by [MCP Analytics](https://mcpanalytics.ai) | Powered by R & Python

</div>

---

If MCP Analytics saves you time, a ⭐ on GitHub helps others find it.

**Tags**: `mcp` `mcp-server` `model-context-protocol` `analytics` `data-analytics` `shopify-analytics` `stripe-analytics` `csv-analysis` `statistics` `machine-learning` `time-series` `clustering` `regression` `business-intelligence` `claude` `cursor` `ai-tools` `no-code-analytics` `forecasting` `customer-analytics`