MCP Hub
Back to servers

aicoreutils

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

Registryglama
Stars
1
Updated
May 4, 2026

Quick Install

uvx aicoreutils

AICoreUtils

AI-CLI MCP server

中文说明

AICoreUtils 是一个面向 LLM Agent 的 JSON 优先命令行工具包原型。它参考 GNU Coreutils 的常用命令,但不是完整的 GNU 兼容替代品。

项目目标是给机器调用方提供确定、低噪音、易解析的 CLI 接口:

  • 默认输出 JSON
  • 错误以 JSON 写入 stderr
  • 退出码语义稳定
  • 修改文件的命令支持 --dry-run
  • 需要管道组合时显式使用 --raw

快速开始

pip install aicoreutils
aicoreutils schema --pretty
aicoreutils ls . --limit 20
aicoreutils rm build --recursive --dry-run

🤖 Claude Desktop / MCP 集成

一行配置,让 Claude 直接操作你的文件系统:

编辑 Claude Desktop 配置文件(详细说明 →):

系统配置文件
macOS~/Library/Application Support/Claude/claude_desktop_config.json
Windows%APPDATA%\Claude\claude_desktop_config.json
Linux~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "aicoreutils": {
      "command": "python",
      "args": ["-m", "aicoreutils.mcp_server"]
    }
  }
}

重启 Claude Desktop,然后对它说:

"列出项目里所有 Python 文件,统计代码行数"

Claude 自动调用 aicoreutils ls + aicoreutils wc,全程 JSON 交互。

更多集成方式:aicoreutils tool-list --format openai 输出 OpenAI Function Calling 格式,可直接用于任意 Agent 框架。

运行测试

# 推荐主入口(pytest,含 Hypothesis property-based 测试和 GNU 对照测试)
python -m pytest project/tests/ -v --tb=short

# Legacy 入口(unittest,部分运行器)
python -m unittest discover -s project/tests -v

项目结构

.
|-- src/aicoreutils/        # Python 包源码
|-- .github/               # CI、Copilot 指令和开发脚本
|-- pyproject.toml         # 包元数据和构建配置
|-- README.md              # 项目入口
`-- project/               # 项目附属资源
    |-- tests/             # 子进程级行为测试
    |-- docs/              # 文档入口和分类文档目录
    |   |-- reference/     # 协议、命令面和安全生产契约
    |   |-- guides/        # 使用指南
    |   |-- audits/        # 兼容性和质量审计
    |   |-- development/   # 测试和开发说明
    |   |-- status/        # 当前项目状态(唯一权威来源)
    |   |-- analysis/      # 项目分析日志(历史归档)
    |   |-- agent-guides/  # AI 辅助编码与文档治理规则
    |   `-- reports/       # 测试报告等生成/归档文档
    |-- vendor/gnu-coreutils/  # 本地上游源码缓存,默认被 Git 忽略
    `-- AGENTS.md          # 仓库级 Agent 入口规则

文档

发布状态

当前实现:aicoreutils schema 中登记 114 个 CLI 命令(含 tool-list 等 Agent 元命令)。

重要限制:本项目是受 GNU Coreutils 启发的 Agent 友好子集,不是完整的 GNU Coreutils 克隆。


English

AICoreUtils is a JSON-first command-line toolkit prototype for LLM agents. It is inspired by common GNU Coreutils commands, but it is not a complete GNU-compatible replacement.

The goal is a deterministic, low-noise interface for machine callers:

  • JSON output by default
  • JSON errors on stderr
  • Stable semantic exit codes
  • --dry-run for mutation commands
  • Explicit --raw output for pipeline composition

Quick Start

pip install aicoreutils
aicoreutils schema --pretty
aicoreutils ls . --limit 20
aicoreutils rm build --recursive --dry-run

🤖 Claude Desktop / MCP Integration

One config line to let Claude operate your filesystem:

Edit Claude Desktop config (full guide →):

OSConfig File
macOS~/Library/Application Support/Claude/claude_desktop_config.json
Windows%APPDATA%\Claude\claude_desktop_config.json
Linux~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "aicoreutils": {
      "command": "python",
      "args": ["-m", "aicoreutils.mcp_server"]
    }
  }
}

Restart Claude Desktop, then ask:

"List all Python files in the project and count lines of code"

Claude calls aicoreutils ls + aicoreutils wc automatically.

For other frameworks: aicoreutils tool-list --format openai outputs OpenAI Function Calling format directly.

Run tests

# Recommended primary entry (pytest, includes Hypothesis property-based and GNU differential tests)
python -m pytest project/tests/ -v --tb=short

# Legacy entry (unittest, partial runner)
python -m unittest discover -s project/tests -v

Project Layout

.
|-- src/aicoreutils/        # Python package
|-- .github/               # CI, Copilot instructions and development scripts
|-- pyproject.toml         # package metadata and build config
|-- README.md              # project entry point
`-- project/               # project collateral
    |-- tests/             # subprocess-level behavior tests
    |-- docs/              # documentation index and categorized docs
    |   |-- reference/     # protocol, command-surface and security contracts
    |   |-- guides/        # usage guides
    |   |-- audits/        # compatibility and quality audits
    |   |-- development/   # testing and development notes
    |   |-- status/        # current project status (single authoritative source)
    |   |-- analysis/      # project analysis logs (historical archive)
    |   |-- agent-guides/  # AI coding assistant and docs governance rules
    |   `-- reports/       # test reports and archived generated docs
    |-- vendor/gnu-coreutils/  # local upstream source cache, ignored by Git by default
    `-- AGENTS.md          # repository-level agent entry rules

Documentation

Release Status

Current implementation: 114 CLI commands in aicoreutils schema (including agent-native meta-commands like tool-list).

Important limitation: this project is an agent-friendly subset inspired by GNU Coreutils, not a full GNU Coreutils clone.

Reviews

No reviews yet

Sign in to write a review