Atlas / Skills / youngsu-kim / macaulay2-mcp

macaulay2-mcpSAFE

skills/youngsu-kim/macaulay2-mcp

MCP server providing a persistent Macaulay2 1.26 session to Claude Code, opencode, LM Studio, and any MCP client

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
1 documented
License
GPL-3.0
Stars
0
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Motivation

The goal for the Macaulay2-MCP project is to leverage large-language-models when working with Macaulay2. Especially, it should lower the entry point for newcomers or test a few lines of code. It is still under development; use it at your own risk and share your thoughts with me.

The current version is under testing. This early version is published on GitHub to test other components such as PyPI, LM Studio linking, and Binder.

Philosophy

  • Nearly all commands and programs below are non-invasive and reversible.
  • The program is not designed to make decisions but inform the users of options.
  • At some point, this MCP should work together with Lean-LSP.
  • It will be updated on an as-needed basis.

Acknowledgments

The project is largely developed under the author's guidance by Qwen 3.8 models hosted at National Research Platform. Also, the author thanks Dr. Mary Thomas and other leaders at the San Diego Supercomputer Center. The author learned a large portion of the skills used in this project from their CyberInfrastructure Professional Development Training Program.

Introduction

Use Macaulay2 from your AI coding assistant.

macaulay2-mcp is an MCP (Model Context Protocol) server that gives Claude Code, opencode, LM Studio, and any other MCP client a persistent Macaulay2 session: ask your assistant to compute Groebner bases, resolutions, Betti tables, primary decompositions, Hilbert polynomials — and it runs the computations in a real M2 kernel, with state (rings, ideals, your definitions) preserved across calls.

Three notations, one kernel — raw M2 syntax, plain English, LaTeX. Each ask is self-contained (paste any one into a fresh session), and the trailing memory line is genuine output (every m2_evaluate result ends with the kernel's resident/peak):

[![macaulay2-

Read from source at commit 50c4b9dd5d4eOBSERVED · 2026-10-12
02

Install

Commands as the repository documents them. They are shown, not run.

uv sync                      # install/refresh deps
uv run pytest -q             # full test suite (needs M2 1.26 installed)
uv run ruff check src tests  # lint
uv run macaulay2-mcp selftest# one-command install verification
uv run macaulay2-mcp         # run the MCP server on stdio
claude mcp add macaulay2 -- uvx macaulay2-mcp
03

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (4)

MEDIUMInventory / provenance · skill.no_skill_md · CWE-1104
Why it matters. no SKILL.md at the audited path
Fix. a skill without its instruction file cannot be reviewed as one
LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427
README.md:188
* **Audit journal.** Every MCP↔M2 exchange is appended to a JSONL file at `./.m2-mcp/session-<UTC>-<pid>.jsonl` in your project: the code, M2's output, timings, refused gate attempts, and the MCP clie
Why it matters. an instruction to move sensitive data to an outside destination
Fix. remove; a skill never needs the user's secrets off the machine
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:77
| [uv](https://docs.astral.sh/uv/) (runs the server, no install) | `brew install uv` | `curl -LsSf https://astral.sh/uv/install.sh \| sh` |
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
docs/installation.md:34
(`curl -LsSf https://astral.sh/uv/install.sh | sh`, installing to

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 50c4b9dd5d4efull audit observations/trust-audit/skill/youngsu-kim__macaulay2-mcp.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-1250c4b9dd5d4eSAFEB89first audit
06

Questions

What does the macaulay2-mcp skill do?

MCP server providing a persistent Macaulay2 1.26 session to Claude Code, opencode, LM Studio, and any MCP client

Is macaulay2-mcp safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can macaulay2-mcp access on my machine?

The audit observed that it reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does macaulay2-mcp work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (50c4b9dd5d4e), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement