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 → • Try Demo → • Pricing →

Hire the team. Own the analysis. Rerun forever.

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

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

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 validated pipeline — you choose how far it goes:

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 →

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, validated 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, go to account settings, and copy your API key (starts with mcp_). You get 2,000 welcome credits — no credit card required.

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):

{
  "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:

{
  "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:

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:

{
  "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:

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

Browse Tools First (No Account Needed)

Explore the full tool catalog before signing up:

# 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 validated 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: progress, queue position, report link
• run_analysis - Re-run an analysis you own (or one discovered via discover_tools) on fresh data
• modify_analysis - Request changes to an existing analysis
• module_request - Request a new analysis capability

Discovery

• discover_tools - Natural language tool discovery (semantic search)
• 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
• report_cards / cards_list / cards_customize / cards_reset - Display and customize individual report cards
• agent_advisor - Conversational AI that guides analysis and interprets results

Platform Tools

• billing - Usage and credit management
• account_link - Link your MCP client to your account
• 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

Statistical Methods

• Regression Analysis
• Advanced Modeling
• Hypothesis Testing
• Survival Analysis
• Bayesian Methods

Machine Learning

• Ensemble Methods
• Boosting Algorithms
• Neural Networks
• Clustering
• Dimensionality Reduction

Time Series

• Forecasting
• Seasonal Analysis
• Trend Detection
• Multivariate Models
• Causal Analysis

Business Analytics

• Customer Analytics
• Market Analysis
• Pricing Models
• Predictive Analytics
• Experimental Design

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 - Credits, tiers, and plans
• How Credits Work - The credit model explained
• Security - Security & compliance details
• Tutorials - Step-by-step guides

Support

• Issues: GitHub Issues
• Email: [email protected]
• Docs: mcpanalytics.ai/docs
• Enterprise: [email protected]

Comparison with Other MCP Servers

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

# 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: [email protected]

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 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
• Privacy Policy

Ready to transform your data analysis workflow?

Get Started Free | Read Docs | View Demo

Built by MCP Analytics | Powered by R & Python

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