Wolfram Alpha MCP Server

This MCP server provides a direct connection to the Wolfram Alpha API, allowing your AI assistant to leverage Wolfram's powerful computational knowledge engine. It enables your assistant to perform complex calculations, solve mathematical problems, access scientific data, and answer factual queries with precision by tapping into Wolfram Alpha's vast knowledge base. Similar to the "!wa" bang command in DuckDuckGo search, this integration enhances your assistant's capabilities with accurate, computation-based responses for technical, scientific, and mathematical questions.

Overview

The Wolfram Alpha MCP server connects your AI assistant to Wolfram Alpha's computational intelligence engine, providing access to a vast knowledge base for mathematical, scientific, and factual queries.

Prerequisites

Before using this MCP server, you need to:

Obtain a Wolfram Alpha API key from Wolfram Alpha Developer Portal
Have Python installed on your system

Installation

Option 1: Install from PyPI

pip install mcp-wolfram-alpha

Option 2: Install from Source

Clone the repository:

git clone https://github.com/SecretiveShell/MCP-wolfram-alpha.git
cd MCP-wolfram-alpha

Install the package:

pip install -e .

Option 3: Use Docker

docker pull ghcr.io/secretiveshell/mcp-wolfram-alpha:latest
docker run -e WOLFRAM_API_KEY=your-api-key -p 8000:8000 ghcr.io/secretiveshell/mcp-wolfram-alpha:latest

Configuration

You must set the WOLFRAM_API_KEY environment variable with your Wolfram Alpha API key. This MCP was tested with the full results API, but a simpler API might also work.

Add the following configuration to your MCP client (Claude Desktop, Cursor, etc.):

{
    "mcpServers": {
        "MCP-wolfram-alpha": {
            "command": "uv",
            "args": [
                "--directory",
                "PATH_TO_YOUR_PROJECT_DIRECTORY",
                "run",
                "MCP-wolfram-alpha"
            ],
            "env": {
                "WOLFRAM_API_KEY": "your-app-id"
            }
        }
    }
}

Replace PATH_TO_YOUR_PROJECT_DIRECTORY with the full path to where you installed the MCP server, and your-app-id with your actual Wolfram Alpha API key.

Usage

Once configured, your AI assistant can use Wolfram Alpha to answer computational questions. You can prompt your assistant with queries like:

"Calculate the derivative of x^2 * sin(x)"
"What is the distance from Earth to Mars right now?"
"Solve the equation 3x^2 + 2x - 5 = 0"
"What is the boiling point of mercury?"
"Convert 150 pounds to kilograms"

The assistant will use the Wolfram Alpha API to provide accurate, computation-based answers.

Debugging

For debugging purposes, you can use mcp-cli-inspector:

Create a config.json file with your server configuration
Run:

npx @wong2/mcp-cli -c ./config.json

This allows you to test the MCP server directly without going through an AI assistant.