Wolfram Alpha MCP by SecretiveShell
SecretiveShellLABSCO SUMMARY
A knowledge engine, plus a worked client.
The server itself is a thin single-purpose bridge to Wolfram Alpha. What makes the repository worth cloning is that it ships the rest of the loop — a Gemini client, a Gradio UI, and Dockerfiles for both — so you can watch an LLM consume Wolfram results before wiring anything into your own stack.
What it is
An MCP server that fronts the Wolfram Alpha API, so a chat application can send computational queries and get structured knowledge back instead of relying on the model's own recall. The repository also ships the other half of the loop: an MCP client example built on Gemini via LangChain, and a Gradio web interface for switching between Wolfram Alpha, Google AI and query history.
What you get
- Math, science and data questions answered by Wolfram Alpha's engine rather than from the model's memory
- A Gradio web interface that switches between Wolfram Alpha, Google AI (Gemini) and past queries
- A command-line client that drives the same server, runnable directly or from a Docker image
- A VS Code entry point: a
.vscode/mcp.jsonin your project root, modelled on the template atconfigs/vscode_mcp.json
Requirements
A Wolfram Alpha AppID in WOLFRAM_API_KEY. GeminiAPI is only needed for the bundled Gemini client and the Gradio UI, not for the server itself. Install is a clone plus pip install -r requirements.txt, or uv sync; the pyproject names the package mcp-wolframalpha at 0.1.0. Claude Desktop launches it with python3 against src/core/server.py.
Setup effort
Build from source — git clone https://github.com/akalaric/mcp-wolframalpha.git
USE CASES
01
Answering a math or physics question exactly
Send the question to Wolfram Alpha's engine and get its computed answer, instead of trusting a formula the model half-remembers.
02
Looking up curated data mid-conversation
Query units, constants, chemistry or country-level statistics through the server the chat client is already connected to.
03
Seeing the whole loop before you build one
Run the bundled Gemini client — command line or Gradio UI — against the server and watch how the model uses what comes back.
04
Adding Wolfram to VS Code
Create .vscode/mcp.json in the project root from the template the repository ships at configs/vscode_mcp.json.
BEFORE YOU INSTALL
What to know first
Requires
- Python 3.10 or later
- WOLFRAM_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/akalaric/mcp-wolframalpha.git
cd mcp-wolframalpha
pip install -r requirements.txtCreate a .env file in the clone containing WOLFRAM_API_KEY=<YOUR_WOLFRAM_API_KEY> (your Wolfram Alpha AppID)
Add the Claude Desktop block below, where <YOUR_PATH_TO_SRC>/core/server.py is the full path of src/core/server.py in your clone, and restart Claude Desktop
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"WolframAlphaServer": {
"command": "python3",
"args": [
"<YOUR_PATH_TO_SRC>/core/server.py"
]
}
}
}<YOUR_PATH_TO_SRC>/core/server.py is the full path of src/core/server.py in your clone.
The configuration on this page does not set WOLFRAM_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.
