Wolfram Alpha

You run a Wolfram Alpha MCP Server to access Wolfram Alpha mobile API capabilities through the Model Context Protocol (MCP). It enables scientific calculations, step-by-step math explanations, multi-format outputs, and real-time streaming for an interactive experience.

How to use

To use this MCP server with your MCP client, start the server locally or via a remote MCP runner, then configure your client to connect to it. You can perform basic queries, advanced queries, and receive streaming results for a responsive experience.

Try the basic and advanced query tools to see how the server handles mathematical and scientific questions, including formatted outputs and streaming responses.

Example usage patterns you can try in your client code (Python-like pseudocode):

# Basic query
result = await wolfram_alpha_query("What is the derivative of x^2?")

# Advanced query with custom format
result = await wolfram_mobile_query(
    query="plot sin(x)",
    format_type="plaintext",
    output_type="json"
)

# Step-by-step solution for a math problem
result = await wolfram_step_by_step("solve x^2 + 5x + 6 = 0")

# Streaming query for real-time data
result = await wolfram_streaming_query("What is the integral of x^2?")
import json
data = json.loads(result)
for chunk in data['streaming_chunks']:
    print(f"[{chunk['type']}] {chunk['content']}")

# Streaming step-by-step solution
result = await wolfram_streaming_step_by_step("solve x^2 + 5x + 6 = 0")
data = json.loads(result)
for chunk in data['streaming_chunks']:
    print(f"[{chunk['type']}] {chunk['content']}")

How to install

Prerequisites: you need Python and pip installed on your system.

From PyPI you can install the MCP server package with a single command.

pip install wolfram-alpha-mcp-server

If you prefer to install from source, clone the repository and install in editable mode.

git clone https://github.com/your-username/wolfram-alpha-mcp-server.git
cd wolfram-alpha-mcp-server
pip install -e .

Start the MCP server using the provided entry point. You can run a remote version or use the CLI tool.

python server_remote.py

wolfram-alpha-mcp

Configuration and examples

Configure your MCP client to load the Wolfram Alpha MCP server. Use the following JSON as a starting point for your MCP client configuration.

{
  "mcpServers": {
    "wolfram-alpha": {
      "command": "uvx",
      "args": ["wolfram-alpha-mcp-server@latest"]
    }
  }
}

If you want to run a localized instance with a specific package/version, you can reference the dedicated server command similarly.

{
  "command": "uvx",
  "args": ["wolfram-alpha-mcp-server-xiaomayisjh@latest"]
}

Available tools

wolfram_alpha_query

Basic query tool for scientific and factual information lookup.

wolfram_mobile_query

Advanced query tool supporting custom formats and parameters.

wolfram_step_by_step

Tool that provides detailed step-by-step solutions for math problems.

wolfram_streaming_query

Streaming query tool that delivers real-time responses.

wolfram_streaming_step_by_step

Streaming, step-by-step solution tool for math problems.