mcp-mma-docs
Categories
Language:
Python
Stars:
5
Forks:
1
Mathematica Documentation MCP server
General & Usage
Made with FastMCP
Requirements: pip install -r requirements.txt
and have Mathematica installed (or at least wolframscript
callable from terminal, e.g. via free wolfram engine for developers).
Run fastmcp dev path/to/mcp-mma-doc.py
to initialize the server.
Run fastmcp install path/to/mcp-mma-doc.py
to install to claude or add following to claude/cline config:
"mathematica-docs": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"/path/to/mcp-mma-doc.py"
]
}
- If you need custom path to
wolframscript
, you can set via changing line 6 in the python filewolframscript='wolframscript'
towolframscript='/path/to/wolframscript'
.
Tools
The plugin provides the following commands:
- get_docs: support factory functions, function via an addon, and function via a package.
- Basic usage: get_docs("Plot")
- With package: get_docs("WeightSystem", packages=["LieART"])
- With addon: get_docs("FCFeynmanParametrize", packages=["FeynCalc"], load_addons=["FeynArts"])
- list_package_symbols: list all symbols/functions in a package.
- Basic usage: list_package_symbols("FeynCalc")
Known issues
- If you see things like
INFO Processing request of type __init__.py:431 ListToolsRequest
in cline, you can ignore them as this will not affect it from working, this is due to current incomplete impliementation of the function discription and listing support via current usage of FastMCP. - Some MMA docs may contain complex styling format, and is not easy to remove with simple regex, your llm may be influenced by this, please instruct it to ignore the styling format and write in InputForm only.
Screenshots
Publisher info
benhaotang
Graduate student in Theoretical Physics @Uni-Heidelberg
More MCP servers built with Python
Create, backtest, and execute trades directly in one chat box. The Composer MCP Server gives LLMs the power to backtest investment ideas and execute automated trading strategies. Trade across stocks, ETFs, and crypto directly in Claude.
An MCP to generate presentations with AI. Create and edit PowerPoint presentations with AI.
The PaddleOCR MCP server brings enterprise-grade OCR and document parsing capabilities to AI applications. Built on PaddleOCR — a proven solution with 50,000+ GitHub stars, deeply integrated by leading projects like MinerU, RAGFlow, and OmniParser— with targeted optimizations based on the MCP concept.