mcp-mma-docs
MCP server for checking Mathematica documentation via local MMA installation
claude mcp add --transport stdio benhaotang-mcp-mma-docs uv run --with mcp mcp run /path/to/mcp-mma-doc.py \ --env WOLFRAMSCRIPT_PATH="path to wolframscript executable (if not in PATH)"
How to use
This MCP server provides automatic Mathematica/Wolfram documentation generation. It uses the Python-based MCP SDK to expose functions that generate docs for Mathematica symbols, packages, and add-ons. The available tools include get_docs for retrieving documentation from a symbol, package, or addon, and list_package_symbols to enumerate all symbols within a given package. To run the server, use the MCP runner (e.g., uv-based setup) and point it at the mcp-mma-doc.py script. Once running, you can query the server using the standard MCP tooling to fetch documentation for Mathematica functions or packages, or to list symbols for a package such as FeynCalc or LieART. Note that you may need a working Wolfram environment (wolframscript) for documentation extraction, and you can configure the path to wolframscript if it’s not in your system PATH.
How to install
Prerequisites:
- Python 3.8+ and pip
- Mathematica installed or wolframscript accessible from the command line
- Network access if dependencies must be fetched
- Clone the repository or download the project files.
- Create and activate a Python virtual environment (optional but recommended):
- python -m venv venv
- source venv/bin/activate # on macOS/Linux
- venv\Scripts\activate # on Windows
- Install Python dependencies:
- pip install -r requirements.txt
- Ensure wolframscript is accessible. If it’s not in PATH, set the path via an environment variable or MCP config (WOLFRAMSCRIPT_PATH).
- Run the MCP server in development mode (example):
- mcp dev path/to/mcp-mma-doc.py
- To install or configure in Claude, use the provided installation snippet and adjust the command to your environment (uv-based or direct mcp path as needed).
Notes:
- If you’re using uv in Claude, you may need to adjust the command path to the mcp wrapper as described in the README to avoid platform-specific CLI parsing issues.
- Ensure you have the required Mathematica tooling available and properly licensed where applicable.
Additional notes
Tips and caveats:
- Environment variable: If wolframscript isn’t in your PATH, set WOLFRAMSCRIPT_PATH in the MCP config or export it in your shell before starting the server.
- When installing via Claude, if you encounter issues with the uv-based command on certain Linux/macOS setups, switch to invoking the exact mcp executable path as shown in the README snippet.
- This server relies on the Python SDK; you may see some verbose console output related to the cline tool. It does not affect documentation retrieval or function calls.
- Keep your Mathematica/Wolfram environment up to date to ensure compatibility with the generated documentation.
Related MCP Servers
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
mcp-yfinance
Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp
servicenow-api
ServiceNow MCP Server and API Wrapper
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools