# Monte statistics

> Monte statistics is a free MCP server for analytics and data. Interactive statistics lessons and solvers for students and self-learners, with a free MCP. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** Web, API
- **Website:** https://monte.markets
- **Repository:** https://github.com/skirberg/monte/tree/HEAD/mcp
- **MCP Registry name:** io.github.skirberg/monte
- **Categories:** [analytics and data](https://ai-powered.com/categories/analytics-and-data), [education and exams](https://ai-powered.com/categories/education-and-exams)
- **Listing updated:** 2026-11-19

## About

Monte is a free set of statistics lessons covering fourteen topics, from data sampling and probability through regression. Each topic pairs a short plain-language explanation with a worked example, a draggable visual, and timed practice drills that generate new numbers.

Beyond the lessons, the site includes a glossary, a 20-question mock test, and a set of small games that illustrate ideas such as the house edge and the long run. The MCP server exposes eleven solvers that work through calculations step by step, so an AI client can show its working rather than just return an answer.

The project suits students revising introductory statistics, teachers looking for visual demonstrations, and developers who want an assistant to explain statistical calculations. The MCP endpoint is read-only and needs no API key, according to its registry entry.

## Features

- **Fourteen statistics topics:** Lessons run from data and sampling through the normal curve, confidence intervals, hypothesis tests and regression.
- **Interactive visual demos:** Draggable and clickable visuals illustrate ideas like the normal distribution and the central limit theorem.
- **Timed practice drills:** Drills regenerate fresh numbers each time so learners can repeat exercises.
- **Mock test:** A 20-question practice test covers the material across topics.
- **Step-by-step solvers:** Eleven solvers show every calculation step, available through the MCP server.
- **Read-only MCP endpoint:** The streamable HTTP server is read-only and requires no key, per its registry entry.

## Good for

- Revising introductory statistics before an exam
- Showing students a visual demonstration of the normal curve or sampling
- Getting step-by-step working for a probability or regression calculation inside an AI client
- Practising timed statistics drills with fresh numbers

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http monte https://mcp.monte.markets/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.monte.markets/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "monte": {
      "url": "https://mcp.monte.markets/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "monte": {
      "type": "http",
      "url": "https://mcp.monte.markets/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "monte": {
      "serverUrl": "https://mcp.monte.markets/mcp"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://mcp.monte.markets/mcp
```

Enter a Name (for example "Monte statistics"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "monte": {
      "type": "http",
      "url": "https://mcp.monte.markets/mcp"
    }
  }
}
```

## Tools

All 8 tools say they're read-only. From the server's own tool annotations; not verified by us.

- `list_topics` (says read-only): The 14 statistics topics on Monte, in order, with their page links.
- `get_topic` (says read-only): One topic in plain English: the idea, why it matters, a worked example, the usual trap, the formulas and the five lessons, with links.
- `search_terms` (says read-only): Statistics terms in plain English with an example each, matched on the term or its meaning.
- `list_solvers` (says read-only): The 11 solvers and the inputs each one takes (key, label, default value, and choices where there are some). Use with solve.
- `solve` (says read-only): Runs one of Monte's solvers and returns every answer with its working, exactly as the solver page shows it. Inputs you leave out keep the solver's defaults. Numbers may be written as 0.7, 70% or 7/10.
- `test_result` (says read-only): For a positive result, the chance you really have the thing, from how common it is, how often the test catches it and how often it false-alarms (Bayes).
- `warranty` (says read-only): Expected cost of buying versus skipping a warranty or insurance plan, the break-even chance and the plan's markup.
- `ab_test` (says read-only): Two-proportion z test for an A/B test: the two rates, the lift, the p-value, a 95% range for the difference, and visitors needed per version to detect this gap.

## FAQ

### Does the MCP server need an API key?

No. The registry entry says it is read-only and needs no key.

### How many topics does the site cover?

The site lists fourteen topics, from data and sampling to multiple regression.

### How many solvers does the MCP server offer?

The registry entry describes eleven solvers that show every step.

### Is Monte statistics free?

Yes. Monte statistics is free to use.

### How do I add Monte statistics to Claude Code?

Run this command in your terminal: claude mcp add --transport http monte https://mcp.monte.markets/mcp

### What are the best alternatives to Monte statistics?

The closest alternatives to Monte statistics are ProvenDecisions optimization solver, UK Data: Maths and statistics, Moltline Educator Toolkit, Data Compute Stats Mcp and MCP Analytics.

## Where this comes from

- Description: written from the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 20 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [ProvenDecisions optimization solver](https://ai-powered.com/mcp/provendecisions-optimization-solver): ProvenDecisions optimization solver is a freemium MCP server for analytics and data.
- [UK Data: Maths and statistics](https://ai-powered.com/mcp/uk-data-maths-and-statistics): UK Data: Maths and statistics is a freemium MCP server for analytics and data.
- [Moltline Educator Toolkit](https://ai-powered.com/mcp/moltline-educator-toolkit): Moltline Educator Toolkit is a freemium MCP server for education and exams.
- [Data Compute Stats Mcp](https://ai-powered.com/mcp/data-compute-stats-mcp): Data Compute Stats Mcp is a freemium MCP server for analytics and data.
- [MCP Analytics](https://ai-powered.com/mcp/mcp-analytics): MCP Analytics is an MCP server for analytics and data.
- [Databutler Stats](https://ai-powered.com/mcp/databutler-stats): Databutler Stats is an MCP server for analytics and data.
- [Cursos gratis en español](https://ai-powered.com/mcp/cursos-gratis-en-espanol): Cursos gratis en español is a free MCP server for education and exams.
- [Fox River Press](https://ai-powered.com/mcp/fox-river-press): Fox River Press is an open-source MCP server for analytics and data.

---
Source: https://ai-powered.com/mcp/monte-statistics
