Wolfram Language MCP
Enables mathematical computation via Wolfram Language/Mathematica integration, supporting calculations, equation solving, calculus, matrix operations, and symbolic mathematics.
README
Wolfram Language MCP Server
A Model Context Protocol (MCP) server that provides powerful mathematical computation capabilities via Wolfram Language/Mathematica integration. Built with FastMCP for seamless integration with Claude Desktop.
Features
- Mathematical Calculations - Evaluate complex expressions
- Equation Solving - Solve algebraic and differential equations
- Calculus Operations - Integration and differentiation
- Matrix Operations - Linear algebra computations
- Statistical Analysis - Statistical measures and data analysis
- Symbolic Mathematics - Simplify, factor, and expand expressions
- Arbitrary Code Execution - Execute any Wolfram Language code
- Data Visualization Workflow - Generate data with Wolfram, visualize with React/Python
Prerequisites
- Python 3.10+
- Wolfram Mathematica 14.0+ or Wolfram Engine (free for developers)
- Claude Desktop
Installation
1. Install Wolfram Mathematica or Wolfram Engine
Option A: Wolfram Mathematica (Commercial)
- Download from Wolfram Research
Option B: Wolfram Engine (Free for developers)
- Download from Wolfram Engine
- Requires free license activation
2. Install the MCP Server
# Clone the repository
git clone https://github.com/paraporoco/Wolfram-MCP.git
cd Wolfram-MCP
# Create virtual environment
python -m venv venv
# Activate virtual environment
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt
3. Configure Claude Desktop
Add to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"wolfram": {
"command": "C:\\Users\\YOUR_USERNAME\\Projects\\Wolfram-MCP\\venv\\Scripts\\python.exe",
"args": [
"C:\\Users\\YOUR_USERNAME\\Projects\\Wolfram-MCP\\wolfram_mcp_server.py"
]
}
}
}
Note: Adjust paths according to your installation location.
4. Verify Installation
Restart Claude Desktop and ask:
Can you test the Wolfram connection?
Claude should use the wolfram_test_connection tool and report success.
Available Tools
| Tool | Description | Example |
|---|---|---|
wolfram_calculate |
Evaluate mathematical expressions | 2 + 2, Integrate[x^2, x] |
wolfram_solve |
Solve equations | Solve x^2 - 5x + 6 == 0 for x |
wolfram_integrate |
Compute integrals | Integrate x^2 with respect to x |
wolfram_differentiate |
Compute derivatives | Differentiate x^3 + 2x^2 + x |
wolfram_simplify |
Simplify expressions | Simplify (x^2 - 1)/(x - 1) |
wolfram_factor |
Factor expressions | Factor x^2 - 5x + 6 |
wolfram_expand |
Expand expressions | Expand (x + 1)^3 |
wolfram_matrix_operations |
Matrix computations | Inverse of {{1,2},{3,4}} |
wolfram_statistics |
Statistical analysis | Mean of {1, 2, 3, 4, 5} |
wolfram_execute |
Execute arbitrary Wolfram code | Table[Prime[n], {n, 1, 10}] |
wolfram_test_connection |
Test Wolfram connection | Verify setup |
Visualization Workflow
The Wolfram MCP excels at mathematical computation but returns symbolic representations rather than rendered images. For visual graphs and charts, use the hybrid workflow:
Wolfram (Computation) → Data Extraction → Visualization Tool (Rendering)
📖 Complete Visualization Guide - Comprehensive documentation on creating beautiful, interactive charts
Quick Example
- Generate data with Wolfram:
Table[{x, Sin[x], Cos[x]}, {x, 0, 2*Pi, 0.1}]
- Visualize with React or Python:
- See
examples/trig_visualization.jsxfor interactive React charts - See
examples/trig_plot.pyfor publication-quality matplotlib plots
📁 View All Examples - Complete working examples with code
Usage Examples
Basic Mathematics
What is the integral of x^2?
Solve the equation x^2 - 5x + 6 = 0
Advanced Calculus
Find the derivative of sin(x) * cos(x)
Compute the definite integral of x^2 from 0 to 1
Linear Algebra
Calculate the inverse of the matrix {{1,2},{3,4}}
Find the eigenvalues of {{4,1},{2,3}}
Statistics
What is the mean of the dataset {1, 2, 3, 4, 5}?
Calculate the standard deviation of {10, 20, 30, 40, 50}
Symbolic Math
Simplify (x^2 - 1)/(x - 1)
Factor x^2 - 5x + 6
Expand (x + 1)^3
Configuration
The server defaults to using WolframScript at:
C:\Program Files\Wolfram Research\Mathematica\14.0\wolframscript.exe
To use a different version or location, modify the paths in wolfram_mcp_server.py:
WOLFRAM_SCRIPT_PATH = r"C:\Your\Custom\Path\wolframscript.exe"
MATH_KERNEL_PATH = r"C:\Your\Custom\Path\MathKernel.exe"
Troubleshooting
"Wolfram Language Not Found"
- Verify Mathematica/Wolfram Engine is installed
- Check the paths in
wolfram_mcp_server.pymatch your installation - Ensure Wolfram Engine is activated (run
wolframscriptin terminal)
"Connection Test Failed"
- Make sure your Mathematica license is active
- Try running
wolframscript -code "2+2"in your terminal - Check that the executable path is correct
"Execution Timed Out"
- Complex calculations may need more time
- Use
wolfram_executewith a custom timeout parameter - Consider simplifying the expression
Development
Project Structure
Wolfram-MCP/
├── wolfram_mcp_server.py # Main server implementation
├── requirements.txt # Python dependencies
├── README.md # Documentation
├── LICENSE # MIT License
└── venv/ # Virtual environment (not in git)
Running Tests
# Test the connection directly
python wolfram_mcp_server.py
# Use with Claude Desktop to test all tools
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
MIT License - see LICENSE file for details
Acknowledgments
- Built with FastMCP by Marvin
- Powered by Wolfram Language
- Designed for Claude Desktop
Links
Support
For issues and questions:
- Open an issue on GitHub
- Check existing issues for solutions
- Refer to Wolfram Language documentation for syntax help
Made with ❤️ for the Claude + Wolfram community
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。