Mathematica MCP Server
Enables execution of Wolfram Language code in a secure, session-based environment, with tools for session initialization, code execution, and resource management.
Provides tools for creating sessions, executing Wolfram Language code, and managing session resources within a Mathematica kernel, enabling secure, session-based interaction with Wolfram Language.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mathematica MCP Serversolve the equation x^2 + 3x - 4 = 0"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mathematica MCP Server
This project provides a Model Context Protocol (MCP) server for interacting with a Wolfram Mathematica kernel. It allows Large Language Models (LLMs) to execute Wolfram Language code in a secure, session-based environment.
The animalid folder contains a simple tool for generating unique, animal-based identifiers. Since LLMs often fail to copy UUIDs correctly, this tool replaces them with animal-themed IDs that are more likely to be transcribed accurately.
Tools Provided
create_mathematica_session: Initializes a new Wolfram Language session and returns a unique session ID.execute_mathematica_code: Executes Wolfram Language code within a specified session.close_mathematica_session: Terminates a session and releases its resources.
Related MCP server: applescript-mcp
Prerequisites
Python 3.10 or higher.
uvPython package manager. (Installation guide)A local installation of the Wolfram Engine or Mathematica. The
wolframclientlibrary requires this to function.
Installation & Setup
Set the Security Key:
This server uses a secret key to generate secure session IDs. You must set this as an environment variable.
export ANIMALID_SECRET_KEY='your-super-secret-and-long-key-here'Note: Do not use a weak key or hardcode it in the script.
Usage
To use this server, you need to connect it to an MCP-compatible client, such as Claude for Desktop.
Configure the MCP Client:
Open your client's MCP configuration file (e.g.,
claude_desktop_config.jsonfor Claude for Desktop) and add the following server configuration.Important: Replace
/path/to/your/project/my_mcpwith the absolute path to this project's directory on your system.{ "mcpServers": { "mathematica": { "command": "uv", "args": [ "--directory", "/path/to/your/project/my_mcp", "run", "wolfram_mathematica.py" ], "env": { "ANIMALID_SECRET_KEY": "default-secret-key-for-dev" } } } }You may need to use the full path to the
uvexecutable in thecommandfield if it's not in your system's PATH. You can find it by runningwhich uv(macOS/Linux) orwhere uv(Windows).
screenshot

Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/aac6fef/mathematica_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server