math-mcp-learning-server

Demo

See CONTRIBUTING.md for instructions to record your own demo.

Related MCP server: Math MCP Server

Quick Start

Cloud (No Installation)

Connect your MCP client to the hosted server:

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "math-cloud": {
      "transport": "http",
      "url": "https://math-mcp.fastmcp.app/mcp"
    }
  }
}

Local Installation

{
  "mcpServers": {
    "math": {
      "command": "uvx",
      "args": ["math-mcp-learning-server[scientific,plotting]"]
    }
  }
}

For other installation options (basic, scientific-only, plotting-only), see CONTRIBUTING.md.

Tools

Resources

• math://workspace - Persistent calculation workspace summary

• math://history - Chronological calculation history

• math://functions - Available mathematical functions reference

• math://constants/{constant} - Mathematical constants (pi, e, golden_ratio, etc.)

• math://catalog/tools - Tool catalog with metadata and usage examples

• math://variables - Active variables in the current workspace

• math://test - Server health check

Prompts

• math_tutor - Structured tutoring prompts (configurable difficulty)

• formula_explainer - Formula explanation with step-by-step breakdowns

See Usage Examples for detailed examples.

Development

See CONTRIBUTING.md for development setup, testing, and contribution guidelines.

Security

• OpenSSF Best Practices Silver - Fewer than 1% of open source projects reach this level

• REUSE/SPDX - License compliance for all files

• Signed Commits - GPG-signed commits required

• Dependency Scanning - Automated updates via Renovate

• pip-audit CVE Scanning - Automated dependency vulnerability checks

• gitleaks Secret Scanning - Detects secrets in code and history

• zizmor GitHub Actions Security - Workflow security scanning

• commitlint Enforcement - Conventional commit validation in CI

• OpenSSF Scorecard - Continuous open source security assessment

The calc_expression tool uses restricted eval() with a whitelist of allowed characters and functions, restricted global scope (only math module and abs), and no access to dangerous built-ins or imports. All tool inputs are validated with Pydantic models. File operations are restricted to the designated workspace directory. Complete type hints and validation are enforced for all operations.

Documentation

• Architecture

• Cloud Deployment Guide

• Usage Examples

• Contributing Guidelines

• Maintainer Guide

• Roadmap

• Code of Conduct

• License