macaulay2-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@macaulay2-mcpCompute the Groebner basis of the ideal (x^2 - y^2, x^3 - y^3) over QQ."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
macaulay2-mcp — Binder demo
A zero-install playground for the macaulay2 MCP server.
Click the badge, log in with GitHub (free), wait ~2–4 minutes on the first launch, then open demo.ipynb. The notebook runs the MCP server inside your browser session and drives it with the standard Model Context Protocol — the same way Claude Code or opencode use it on your machine. You can play with Groebner bases, resolutions, Betti tables, and package loading without installing anything.
How it works
This repo only provides the environment (a
Dockerfile) and the demo notebook.At image build time, the
Dockerfileinstalls Macaulay2 1.26 (latest stable, from the official PPA) and uv, and pre-warms the MCP server so sessions start quickly.demo.ipynbis a plain Python 3 notebook (no Macaulay2 Jupyter kernel): its cells act as an MCP client, spawning the MCP server over stdio and calling its tools.
Related MCP server: vMCP
For real work
Binder sessions are temporary (they disappear when you stop using them). For everyday use, install the server on your own machine and connect Claude Code, opencode, Claude Desktop, or Gemini CLI — see the main repository's README:
https://github.com/youngsu-Kim/macaulay2-mcp
License
Same as the main project: GPL-3.0-or-later.
This server cannot be deployed
Maintenance
Related MCP Connectors
Model Context Protocol server for Studex tools, notifications, and profile integrations
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
QuLab MCP remote server (Streamable HTTP) for computational science and lab tools.
Lean 4 MCP server: compile, prove theorems, and formalize math with Mathlib.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables interaction with Jupyter notebooks through the Model Context Protocol, supporting code execution and markdown insertion within JupyterLab environments.181,278BSD 3-Clause
- AlicenseNot gradedqualityDmaintenanceA unified gateway for Model Context Protocol servers, enabling access to multiple scientific computing tools through a single interface.1MIT
- AlicenseNot gradedqualityDmaintenanceAn agent-agnostic MCP server that lets any AI agent drive a local JupyterLab session via the Model Context Protocol.CC BY-4.0
- AlicenseNot gradedqualityDmaintenanceMCP server for executing Python code on CoCalc cloud projects. It enables any MCP-compatible assistant to run Python and machine-learning workloads remotely on CoCalc infrastructure without local GPU requirements.MIT