Math MCP

🚀 Math MCP Server

This is an MCP (Model Context Protocol) server capable of performing basic arithmetic with 64-bit precision and matrix multiplication.

🚀 Quick Start

This Math MCP Server allows you to conduct basic arithmetic operations and matrix multiplication. You can quickly set it up following the steps below.

✨ Features

• Addition
• Subtraction
• Multiplication
• Division
• Matrix multiplication

📦 Installation

Prerequisites

Ensure you have the following installed:

• Python 3.13+
• uv

Installing UV

Refer to the installation guide for all available options.

Unix/MacOS

curl -LsSf https://astral.sh/uv/install.sh | sh

or

brew install uv

Windows

winget install --id=astral-sh.uv  -e

Clone the Repository

git clone https://github.com/avanishd-3/math-mcp.git
cd math-mcp-server
uv sync

💻 Usage Examples

Integration with Clients

Claude Code

fastmcp install claude-code src/math_server.py:math_mcp

Claude Desktop

fastmcp install claude-desktop src/math_server.py:math_mcp

Cursor

fastmcp install cursor src/math_server.py:math_mcp

VS Code

Add the following to .vscode/mcp.json and use your actual path.

{
  "servers": {
    "Math MCP Server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "fastmcp",
        "--with",
        "numpy",
        "fastmcp",
        "run",
        "/absolute/path/Desktop/to/math-mcp-server/src/math_server.py:math_mcp"
      ]
    }
  }
}

🤝 Contributing

1. Fork the repository.
2. Create a new branch:

git checkout -b add-feature

3. Make changes and commit (remember to add unit tests in the test/ directory):

git commit -m "Added a new feature"

4. Push to your fork:

git push origin add-feature

5. Open a pull request.

📚 Documentation

Project Structure

/
├── src
│   └── math_server.py
├── tests
│   ├── test_arithmetic.py
│   │   └── astro.svg
│   ├── test_linear_algebra.py
├── pytest.ini
├── pyproject.toml
└── uv.lock

Architecture

This MCP server uses Fast MCP 2.0, which offers many more features than Fast MCP 1.0, the version used by the official Python SDK for MCP.

Also, the unit tests are written with Pytest, as recommended by Fast MCP 2.0.

Lastly, if you're not aware, uv is a much faster alternative to pip and provides a lockfile for project dependencies (this will be familiar if you've used npm or cargo before). The MCP Python SDK itself uses uv, and it's used for all new Python projects because it's 10 - 100x faster than pip, and the lockfile simplifies dependency version management.