# Math MCP Learning

Math MCP Learning — a hosted MCP server that hands your agent arithmetic, descriptive statistics, unit conversion, matrices and charts. Useful when a task turns numeric.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 579 installs
- Author: clouatre-labs
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/clouatre-labs/math-mcp
- Updated: 2026-04-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/clouatre-labs-math-mcp-learning

## What it does

Nothing runs on your machine here: the server answers at `https://math-mcp--clouatre-labs.run.tools`. Register it once and the agent calls the tools itself whenever numbers show up in a task.

The toolset splits into four groups. `calculate` evaluates a single expression with sin, cos, tan, log, sqrt, abs and pow, while `statistics` returns mean, median, mode, std_dev or variance for a list of numbers. `compound_interest` applies the standard growth formula and `convert_units` covers length, weight and temperature. Every matrix call needs NumPy — run one without it and you get a ValueError. The five chart tools (`plot_function`, `create_histogram`, `plot_line_chart`, `plot_scatter_chart`, `plot_box_plot`) need matplotlib.

Results survive restarts. `save_calculation` stores a named value in the workspace and `load_variable` reads it back in a later session. `plot_financial_line` is the exception worth knowing: the price series it draws is generated for teaching, not taken from any market.

## Requirements
- Remote server: `https://math-mcp--clouatre-labs.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http math-mcp https://math-mcp--clouatre-labs.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add clouatre-labs-math-mcp-learning --url https://math-mcp--clouatre-labs.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "clouatre-labs-math-mcp-learning": {
            "url": "https://math-mcp--clouatre-labs.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "clouatre-labs-math-mcp-learning": {
            "type": "http",
            "url": "https://math-mcp--clouatre-labs.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http clouatre-labs-math-mcp-learning https://math-mcp--clouatre-labs.run.tools
```

## When to use it
- evaluate an expression with sin and sqrt mid-conversation
- pull mean and standard deviation from a list of readings
- convert 150 lb into kilograms
- plot a histogram over a sample
- keep a computed value and reuse it next session

## Example prompts
- Run `compound_interest` for 10000 at 5% over 5 years.
- Save that as `portfolio_return` so I can load it in the next chat.
- Compare the two groups with a box plot.

## Similar
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [statistics-math](https://affpapa.org/en/nevibecode/skills/statistics-math.md) — skill · 434 installs
- [math-tools](https://affpapa.org/en/nevibecode/skills/math-tools.md) — skill · 1 install
- [matplotlib](https://affpapa.org/en/nevibecode/skills/k-dense-ai-matplotlib.md) — skill · 2500 installs
- [data-analysis-jupyter](https://affpapa.org/en/nevibecode/skills/data-analysis-jupyter.md) — skill · 1600 installs
- [seaborn](https://affpapa.org/en/nevibecode/skills/k-dense-ai-seaborn.md) — skill · 2300 installs

## Other versions with the same name
- [Math MCP Learning · clouatre-labs](https://affpapa.org/en/nevibecode/mcp/math-mcp-learning.md) — ★ 7 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
