What runtime dependencies does the server require?
Python (with packages from `requirements.txt`) and Mathematica (or at least `wolframscript` callable from the terminal, e.g., via the free Wolfram Engine for Developers).
@benhaotang
基本情報
MCP server for checking Mathematica documentation via local MMA installation
support factory functions, function via an addon, and function via a package.
list all symbols/functions in a package.
This MCP server integrates Mathematica documentation with AI assistants like Claude. It allows querying documentation for Mathematica functions, including those from packages and add-ons. Built with mcp-python-sdk, it requires Mathematica or a callable wolframscript (e.g., via the free Wolfram Engine for Developers).
After installing the Python requirements (pip install -r requirements.txt) and ensuring Mathematica/wolframscript is available, run mcp dev path/to/mcp-mma-doc.py to initialize the server, or mcp install path/to/mcp-mma-doc.py to install it into Claude. Alternatively, add the corresponding JSON configuration to your Claude or Cline config file. If wolframscript is not in the system path, set the WOLFRAMSCRIPT_PATH environment variable in your shell or MCP config.
Plot.FCFeynmanParametrize from FeynCalc.Python (with packages from `requirements.txt`) and Mathematica (or at least `wolframscript` callable from the terminal, e.g., via the free Wolfram Engine for Developers).
Yes. Set the environment variable `WOLFRAMSCRIPT_PATH` to the full path of your `wolframscript` binary, either in your shell or inside the MCP client configuration.
These are harmless debug messages from the Python SDK that cannot be suppressed. They do not affect the server’s functionality.
Use the `get_docs` tool with the `packages` argument, e.g., `get_docs("WeightSystem", packages=["LieART"])`.
Yes. Provide both the `packages` and `load_addons` arguments to `get_docs`, e.g., `get_docs("FCFeynmanParametrize", packages=["FeynCalc"], load_addons=["FeynArts"])`.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
コメント