The engine

Your agent already knows how to use us.

MCP Analytics is an MCP server: connect it and your AI discovers the tools itself — upload data, commission analyses, track builds, search everything it ever delivered. No SDK, no glue code.

Install → The docs →

What the agent seesthe MCP toolset

▸ datasets_upload  bring the file
▸ create_analysis  plain-English question + depth
▸ build_status  watch it build
▸ run_analysis  re-run on fresh data
▸ ask_library  one answer across every report

discovered automatically over MCPagent-native

Claude

ChatGPT

Cursor

Your Agent

One Config. Direct Access.

Add this to your MCP client configuration and restart.
That's the entire integration.

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

Claude Desktop

Settings > Developer > Edit Config

Cursor

Settings > MCP > Add Server

Other Clients

MCP configuration file

What Your Agent Gets

Direct access to a complete analytics toolkit through standardized MCP tools.

discover_tools

Semantic tool discovery

Find the right analysis tool using natural language. "I need to predict customer churn" returns ranked, compatible tools.

// Example call
discover_tools({
  query: "regression analysis",
  dataset_uuid: "ds_abc123"
})

datasets_upload / datasets_list

Secure data handling

Upload datasets securely with encryption. Read data with filtering, sampling, and column selection. All data encrypted at rest.

// Upload returns UUID + key
datasets_upload({
  prefix: "analysis"
})

run_analysis

Execute any analysis

Run any statistical tool with automatic preprocessing, validation, and AI-narrated insights. Returns shareable report URLs.

// Returns report URL
run_analysis({
  tool_name: "linear_regression",
  taskList: { inputs: {...} }
})

reports_list / reports_list

Query past analyses

Search across all past reports with semantic queries. "What do we know about churn?" finds relevant insights from any analysis.

// Semantic search
reports_list({
  semantic_query: "profit margins"
})

All Standard Analytical Tools

Professional-grade analysis methods, all accessible through the same interface.

Regression

Linear Regression
Ridge / Lasso
Elastic Net
Logistic

Time Series

ARIMA
Prophet
VAR
Exponential Smoothing

ML & Classification

Random Forest
XGBoost
K-Means Clustering
Decision Trees

Hypothesis Testing

T-Test
ANOVA
Chi-Square
Bayesian A/B

Customer Analytics

RFM Segmentation
CLV (BG/NBD)
Churn Prediction
Cohort Analysis

Causal Inference

Causal Impact
Diff-in-Diff
Propensity Matching
Synthetic Control

Economics

Price Elasticity
Demand Forecasting
Market Basket
Association Rules

Survival & Other

Cox Regression
Kaplan-Meier
PCA
Correlation

View All Tools

How It Works

The MCP protocol enables your agent to discover and execute tools autonomously.

Agent Gets Tools

MCP protocol exposes available tools to your agent

User Asks Question

"Analyze sales trends for Q4"

Agent Selects Tool

Discovers and calls appropriate analysis

Results Returned

Report URL + insights for the user

Example Agent Conversation

Can you analyze this sales data and predict next month's revenue?

datasets_upload {"prefix": "sales"}
UUID: ds_sales_12345, ready for analysis

discover_tools {"query": "forecast revenue", "dataset_uuid": "ds_sales_12345"}
Recommended: ARIMA (0.94), Prophet (0.91), Linear Regression (0.87)

run_analysis {"tool_name": "arima", "taskList": {...}}
Report: https://api.mcpanalytics.ai/reports/arima_xyz123

Based on the ARIMA analysis, next month's projected revenue is $847,000 with a 95% confidence interval of $812K-$882K. The model detected strong seasonality...

Enterprise-Grade Security

Built for production. Secure by design.

OAuth 2.0 Authentication

Industry-standard authentication via Auth0. Secure token-based access with automatic refresh. No credentials stored in configs.

Encrypted Data Storage

All datasets encrypted at rest with AES-256. Client-side keys ensure only you can decrypt your data. Auto-expiration available.

Isolated Execution

Each analysis runs in an isolated Docker container. No cross-tenant data access. Automatic cleanup after completion.