NumPy MCP server

The NumPy MCP server provides mathematical calculations and operations through a standardized Model Context Protocol (MCP) interface, making it easy to perform numerical computations directly through Claude or other MCP-compatible LLMs.

Installation Options

Using Claude Desktop

The quickest way to get started is by installing the server directly in Claude Desktop:

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

Manual Setup

This project uses UV for dependency management:

# Install UV if needed
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 and activate virtual environment
uv venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows

# Install dependencies
uv pip install -r requirements.txt

Using the Server

Local Testing

Test the server locally with the MCP Inspector:

mcp dev server.py

Running the Server

For direct execution:

python server.py
# or
mcp run server.py

With Claude Desktop

After installation in Claude Desktop, the server will be available as "NumPy Calculator". You can use it by asking Claude to perform mathematical operations, such as:

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

Available Functions

Basic Arithmetic

• add(a: int, b: int) → int: Add two integers together

Linear Algebra

• matrix_multiply(matrix_a: List[List[float]], matrix_b: List[List[float]]) → List[List[float]]: Multiply two matrices
• eigen_decomposition(matrix: List[List[float]]) → Tuple[List[float], List[List[float]]]: Compute eigenvalues and eigenvectors of a square matrix

Statistics

• statistical_analysis(data: List[float]) → dict[str, float]: Calculate basic statistics for a dataset including:
  • Mean
  • Median
  • Standard deviation
  • Minimum value
  • Maximum value

Data Analysis

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

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.