WOLFRAM

Wolfram MCP Server
for
Local Wolfram Applications

Give LLM systems agentic access to your Wolfram applications

MCP Server for Local Wolfram Applications gives agentic access to your existing Wolfram applications, allowing them to power Wolfram Foundation Tool capabilities in LLM systems.

Requires: Wolfram Engine, Wolfram|One or Mathematica

Works with: Antigravity Claude Code Claude Desktop Cline Continue Cursor LibreChat OpenCode Windsurf Zed Any client that supports MCP

Documentation

Using MCP Server with AI Coding Tools

Using Wolfram MCP Server, AI coding tools such as Claude Code, Cursor and Visual Studio Code can connect to your Wolfram application. Your AI coding assistant can evaluate Wolfram Language code, search Wolfram documentation, read and write notebooks, run tests and inspect code. Quick Start for AI Coding Applications

Using MCP Server with Chat Clients

Connect chat clients such as Claude Desktop to your Wolfram application using MCP Server. Your AI assistant can evaluate Wolfram Language code, answer computational questions through Wolfram|Alpha and access Wolfram documentation. Quick Start for Chat Clients

Mathematics & Computation

Data & Facts

MCP Server for Local Wolfram Applications Q&A

What do I need to use Wolfram MCP Server?

MCP Server for Local Wolfram Applications requires Wolfram Engine, Wolfram|One or Mathematica and an LLM client.

Which of Wolfram's AI products and tools should I use with the MCP Server?

Do I need any additional subscriptions to use MCP Server?

No additional subscriptions are required, but an LLM Kit subscription may enhance results in the included tools.

Can I use Wolfram MCP Server with an AI client that isn't listed in the documentation?

Yes. For other MCP-compatible clients, you can generate the raw JSON configuration and adapt it manually. You can find further instructions in the Quick Start for Chat Clients under Other Chat Clients.

I'm not seeing Wolfram tools in my chat client after following the documentation. What do I do now?

  • Fully restart your chat client after installing (closing the window often just minimizes it to the system tray).
  • Manually inspect the configuration file returned by InstallMCPServer to ensure the server is configured correctly.
  • Check your client's documentation for the location of log files and check for errors.

Why did my computation time out?

The default setting for evaluations is 60 seconds. For long-running computations, you can ask the AI to increase the timeout setting or break your computation into smaller steps.

Why is the MCP Server using a different version of Wolfram Language?

The installed MCP Server will use the same version of Wolfram Language as the session it was installed from. If you want to use a different version of Wolfram Language, you need to install the MCP Server in a session of that version or manually edit the configuration file to point to a different Wolfram kernel.

Why aren't the results I'm getting closer to what I'm looking for?

You can review Writing Persistent Instructions and Tips for Best Results in the Quick Start for Chat Clients. You can also check out Best Practices for AI-Assisted Development in the Quick Start for AI Coding Applications.