Numpy MCP

🚀 NumPy MCP Server

A Model Context Protocol (MCP) server for numerical computation using NumPy

A Model Context Protocol (MCP) server that provides numerical computation, leveraging NumPy for mathematical operations. This server exposes various mathematical tools through the standardized MCP interface, enabling Claude or other MCP-compatible large language models to directly perform numerical calculations.

🚀 Quick Start

This section provides a quick guide on how to get started with the NumPy MCP Server.

✨ Features

• Basic arithmetic operations (addition)
• Linear algebra calculations (matrix multiplication, eigenvalue decomposition)
• Statistical analysis (mean, median, standard deviation, minimum, maximum)
• Polynomial fitting

📦 Installation

Quick Setup with Claude Desktop

The simplest way to install this server is directly within Claude Desktop:

# Install the server in Claude Desktop
mcp install server.py --name "NumPy Calculator"

Manual Installation

This project uses UV for dependency management. To install:

# Install UV if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the repository
git clone https://github.com/yourusername/math-mcp.git
cd math-mcp

# Create a virtual environment and install dependencies
uv venv
source .venv/bin/activate  # On Unix/macOS
# Or
# .venv\Scripts\activate  # On Windows
uv pip install -r requirements.txt

💻 Usage Examples

Development Testing

Test the server locally using the MCP checker:

mcp dev server.py

Claude Desktop Integration

1. Install the server in Claude Desktop:

   mcp install server.py --name "NumPy Calculator"
   

2. The server will now be displayed as "NumPy Calculator" under Claude Desktop.

3. You can use it by having Claude perform mathematical operations, for example:

   • "Calculate the eigenvalues of the matrix [[1, 2], [3, 4]]"
   • "Find the mean and standard deviation of the dataset [1, 2, 3, 4, 5]"
   • "Multiply the matrices [[1, 0], [0, 1]] and [[2, 3], [4, 5]]"

Direct Execution

For advanced usage or custom deployment:

python server.py
# Or
mcp run server.py

📚 Documentation

The server provides support for the following mathematical functions through the MCP interface:

Basic Arithmetic Operations

• add(a: int, b: int) -> int: Adds two integers.

Linear Algebra

• matrix_multiply(matrix_a: List[List[float]], matrix_b: List[List[float]]) -> List[List[float]]: Multiplies two matrices.
• eigen_decomposition(matrix: List[List[float]]) -> Tuple[List[float], List[List[float]]]: Computes the eigenvalues and eigenvectors of a square matrix.

Statistical Analysis

• statistical_analysis(data: List[float]) -> dict[str, float]: Computes basic statistical information for a dataset, including:
  • Mean
  • Median
  • Standard deviation
  • Minimum
  • Maximum

Data Analysis

• polynomial_fit(x: List[float], y: List[float], degree: int = 2) -> List[float]: Fits a polynomial of a specified degree to the given data points.

🔧 Technical Details

Project Structure

The text about project structure seems to be a note for translation rather than actual project structure details. Since there is no real content here, this part is skipped according to the rules.

📄 License

This project is MIT licensed.