MCP.so
Sign In

NumPy MCP Server

@colesmcintosh

About NumPy MCP Server

A Model Context Protocol (MCP) server for numerical computations with NumPy

Basic information

Category

Other

Runtime

python

Transports

stdio

Publisher

colesmcintosh

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "numpy-mcp": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is NumPy MCP Server?

NumPy MCP Server is a Model Context Protocol (MCP) server that exposes mathematical calculations and operations using NumPy. It provides basic arithmetic, linear algebra, statistical analysis, and polynomial fitting through a standardized MCP interface for use with Claude or other MCP-compatible LLMs.

How to use NumPy MCP Server?

Install the server in Claude Desktop with mcp install server.py --name "NumPy Calculator", or clone the repository and set up manually using UV. Once installed, ask Claude to perform operations like "Calculate the eigenvalues of matrix [[1, 2], [3, 4]]" or "Find the mean and standard deviation of [1, 2, 3, 4, 5]". For development testing, use mcp dev server.py.

Key features of NumPy MCP Server

  • Basic arithmetic: addition of two integers
  • Linear algebra: matrix multiplication and eigendecomposition
  • Statistical analysis: mean, median, standard deviation, min, max
  • Polynomial fitting of specified degree to data points
  • Exposes functions through a standardized MCP interface

Use cases of NumPy MCP Server

  • Compute eigenvalues and eigenvectors of a square matrix
  • Calculate mean and standard deviation for a dataset
  • Multiply two matrices and get the result
  • Fit a polynomial curve to given x, y data points
  • Add two integers via an LLM conversation

FAQ from NumPy MCP Server

What mathematical functions does it provide?

It offers addition, matrix multiplication, eigendecomposition, statistical analysis (mean, median, std, min, max), and polynomial fitting.

What are the dependencies?

The server requires NumPy for numerical computations and FastMCP for the MCP server implementation.

How do I install NumPy MCP Server in Claude Desktop?

Run mcp install server.py --name "NumPy Calculator" in your terminal. The server will then appear in Claude Desktop under "NumPy Calculator".

Is this project open source?

Yes, it is licensed under the MIT License.

What kind of data does the server accept?

It accepts numerical data: integers for addition, lists of floats for statistics, and nested lists for matrix operations.

Comments

More Other MCP servers