Aicoreutils

Name: Aicoreutils
Author: caseSHY

by caseSHYcommunityv0.3.6

AICoreUtils is a JSON-first command-line toolkit for LLM agents, inspired by GNU Coreutils, with deterministic JSON output and stable exit codes. It also exposes an MCP server so Claude Desktop and other agent frameworks can call its filesystem-oriented CLI commands.

From the registry: JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support.

GitHub Repository

Install & configure

Prerequisites

required
Install aicoreutils Python package
Install the MCP server package from PyPI so the Python module can be launched.
```
$ pip install aicoreutils
```
https://pypi.org/project/aicoreutils/

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `aicoreutils` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install aicoreutils Python package** — Install the MCP server package from PyPI so the Python module can be launched. Run: `pip install aicoreutils` (https://pypi.org/project/aicoreutils/)

Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","aicoreutils.mcp_server"]

Note: README shows a stdio MCP configuration using the Python module entrypoint. It also mentions an alternative CLI launcher (`aicoreutils-mcp`) with security profiles such as `--profile readonly` or `--profile workspace-write`, but no canonical MCP client config example is provided for that path, so the documented `python -m aicoreutils.mcp_server` form is preferred.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: README shows a stdio MCP configuration using the Python module entrypoint. It also mentions an alternative CLI launcher (`aicoreutils-mcp`) with security profiles such as `--profile readonly` or `--profile workspace-write`, but no canonical MCP client config example is provided for that path, so the documented `python -m aicoreutils.mcp_server` form is preferred.