Quick Start for Chat Clients
Quick Start for Chat Clients
| Recommended Server | Writing Persistent Instructions |
| Installation | Tips for Best Results |
| Understanding the Tools | Troubleshooting |
| Example Use Cases |
This guide walks you through adding Wolfram computational capabilities to chat clients like Claude Desktop. By the end, your AI assistant will be able to evaluate Wolfram Language code, answer computational questions via Wolfram Alpha, and search Wolfram documentation.
For general-purpose chat, use the Wolfram server (the default). It combines code execution with natural language computation.
Claude Desktop
InstallMCPServer["ClaudeDesktop"]Other Chat Clients
MCPServerObject["Wolfram"]["JSONConfiguration"]Verifying the Installation
| WolframContext |
Semantic search across Wolfram resources (documentation, Wolfram Alpha, repositories, and more)
|
| WolframLanguageEvaluator | Execute Wolfram Language code |
| WolframAlpha | Natural language queries to Wolfram Alpha |
You do not need to tell the AI which tool to use. It selects the appropriate tool based on your request.
Mathematics and Computation
Data and Facts
Visualization
Documentation Lookup
Code Assistance
What Are Persistent Instructions?
Persistent instructions are custom text that your chat client sends to the AI at the start of every conversation. They act like standing orders, ensuring the AI always follows your preferences without you having to repeat them.
How to Set Them
What to Include
Ready-to-Use Templates
Copy and paste any of these templates into your persistent instructions. Modify them to suit your needs.
General Computational Use
When I ask mathematical or scientific questions, use Wolfram tools to compute
exact answers rather than approximating. Show the Wolfram Language code you used
so I can learn from it.
For factual questions (population, distance, chemical properties, etc.), use
WolframAlpha for up-to-date data.
When producing plots or visualizations, use clear labels and legends.
Learning Wolfram Language
I am learning Wolfram Language. When I ask how to do something:
1. First use WolframContext to find relevant functions and documentation
2. Write the code using WolframLanguageEvaluator and show me the result
3. Explain each part of the code
4. Suggest related functions I might find useful
Prefer idiomatic Wolfram Language style. Use functional programming patterns
(Map, Select, Fold, etc.) over procedural loops when appropriate. Show
alternative approaches when they exist.
Research and Data Analysis
I use Wolfram tools for research and data analysis. When I ask questions:
- Use WolframAlpha for current data and facts
- Use WolframLanguageEvaluator for computations, statistics, and visualizations
- Always cite the source of factual data (e.g., "According to Wolfram Alpha...")
- When creating visualizations, export them at high resolution
For statistical analysis, show the code and interpret the results in plain
language. Include relevant measures of uncertainty (confidence intervals,
p-values) when appropriate.
Tips for Customizing Instructions
- Be specific about your field or domain (e.g., "I work in signal processing" or "I teach undergraduate calculus")
- Mention output preferences (e.g., "Always show LaTeX-formatted equations" or "Include units in all physical quantities")
- Be specific. "Plot the Bessel function J0 from 0 to 20" works better than "Show me a Bessel function."
- Ask for explanations. "Solve this and explain each step" produces more useful responses than just "Solve this."
- Iterate on visualizations. Start with a basic plot, then refine: "Make the axes larger and add a grid."
- Combine tools. "Look up the formula for black body radiation and then plot it for T = 3000K, 5000K, and 7000K" uses both documentation search and code evaluation.
- Request code. If you want to learn, ask "Show me the Wolfram Language code" to see what the AI runs.
Tools not appearing in chat
- Fully restart your chat client after installing (closing the window often just minimizes it to the system tray)
WolframContext not working as expected
The
tool requires an LLM Kit subscription for full functionality. Without it, Wolfram Alpha results will not be included and the documentation search will be less accurate. The
and WolframAlpha tools work without LLM Kit.
Computation timeouts
By default, evaluations have a 60-second time limit. For long-running computations, ask the AI to increase the timeout or break the computation into smaller steps.
Server is using the wrong 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.