NumPy MCP Server
A Model Context Protocol (MCP) server for numerical computations with NumPy
Overview
NumPy MCP Server is a Model Context Protocol (MCP) server designed for performing numerical computations using the NumPy library. It provides a standardized interface for executing various mathematical operations.
To use the NumPy MCP Server, you can install it directly in Claude Desktop or run it locally. For Claude Desktop, use the command: mcp install server.py --name "NumPy Calculator". For local execution, run python server.py after setting up the environment.
- Basic arithmetic operations (addition) - Linear algebra computations (matrix multiplication, eigendecomposition) - Statistical analysis (mean, median, standard deviation, min, max) - Polynomial fitting
- Performing complex mathematical calculations through a conversational interface.
- Integrating with Claude for real-time numerical analysis.
- Conducting statistical analysis on datasets.
Add to your AI client
Use these steps to connect NumPy MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.
Cursor
Add this to your .cursor/mcp.json file in your project root, then restart Cursor.
.cursor/mcp.json
{
"mcpServers": {
"numpy-mcp-colesmcintosh": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}Claude Desktop
Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"numpy-mcp-colesmcintosh": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"numpy-mcp-colesmcintosh": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"numpy-mcp-colesmcintosh": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"numpy-mcp-colesmcintosh": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"numpy-mcp-colesmcintosh": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-numpy-mcp-colesmcintosh"
]
}
}
}FAQ
What is the primary function of the NumPy MCP Server?
It serves as a server for executing numerical computations using the NumPy library through a standardized MCP interface.
Can I use it for advanced mathematical operations?
Yes! The server supports a variety of operations including linear algebra and statistical analysis.
Is there a specific Python version required?
The server requires Python 3.8 or higher.