# adminmcp
## 基本信息
- Slug: `frankausberlin-adminmcp`
- Source: modelscope
- Publisher: @frankausberlin/adminmcp
- Categories: shell-access / command-line / os-automation
- Hosted: No
- License: Unknown
- Source URL: https://www.modelscope.cn/mcp/servers/@frankausberlin/adminmcp
## 简介
暂无描述。
## 安装提示

```bash
git clone https://github.com/yourusername/adminmcp.git cd adminmcp
```

## MCP Server 详情

# AdminMCP (ACP)

[![Python Version](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.io/)

A comprehensive MCP (Model Context Protocol) based agent environment for system administration and automation tasks. AdminMCP provides both a CLI tool for managing MCP servers and a server implementation with built-in tools and resources for administrative operations.

##  Table of Contents

- [Project Description](#-project-description)
- [Features](#-features)
- [Installation](#-installation)
- [Usage Examples](#-usage-examples)
- [Configuration](#-configuration)
- [Development Setup](#-development-setup)
- [Testing](#-testing)
- [Contributing](#-contributing)
- [License](#-license)

##  Project Description

AdminMCP is a dual-purpose tool that serves as both a command-line interface (CLI) for managing MCP servers and an MCP server itself. The project aims to create a robust environment for system administration tasks through MCP-compatible agents.

The CLI component (`acp`) provides easy management of MCP server processes, while the server component offers a collection of tools and resources for common administrative and computational tasks. Future versions will include client functionality for connecting to and interacting with MCP servers.

### Architecture

- **CLI Tool**: Command-line interface for server lifecycle management
- **MCP Server**: FastMCP-based server providing tools and resources
- **Configuration System**: User-configurable settings stored in `~/.config/adminmcp/`
- **Client** *(Planned)*: MCP client for connecting to servers and executing tasks

##  Features

### Current Features

#### CLI Server Management
- **Server Control**: Start and stop MCP servers as background processes
- **Process Management**: Automatic PID tracking and safe process termination
- **Safety Checks**: Prevents multiple server instances and handles edge cases

#### MCP Server Tools
- **Mathematical Operations**: Add, subtract, multiply, divide numbers
- **Mathematical Constants**: Access to , e,  via resource endpoints
- **Number Utilities**: Check if numbers are even/odd
- **DateTime Resources**: Current datetime with timezone information
- **Wikipedia Integration**: Fetch article summaries from Wikipedia

#### Configuration Management
- **Initialization**: Automated setup of configuration directories
- **User Settings**: Customizable server port and logging levels
- **MCP Server Registry**: Management of connected MCP servers

### Planned Features

#### Client Functionality
- **Server Connection**: Connect to MCP servers via WebSocket/SSE
- **Tool Execution**: Remote execution of server-provided tools
- **Resource Access**: Query server resources programmatically
- **Interactive Mode**: REPL for interactive server interaction

#### Advanced Administration Tools
- **System Monitoring**: CPU, memory, disk usage tools
- **File Operations**: Safe file manipulation tools
- **Network Utilities**: DNS lookup, port scanning, connectivity tests
- **Process Management**: List, start, stop system processes

##  Installation

### Prerequisites

- Python 3.11 or higher
- `uv` package manager (recommended) or `pip`

### Install from Source

1. **Clone the repository:**
   ```bash
   git clone https://github.com/yourusername/adminmcp.git
   cd adminmcp
   ```

2. **Create virtual environment:**
   ```bash
   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   ```

3. **Install dependencies:**
   ```bash
   # Using uv (recommended)
   uv pip install -e .

   # Or using pip
   pip install -e .
   ```

4. **Verify installation:**
   ```bash
   acp --help
   ```

### Using uv (Recommended)

```bash
# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install AdminMCP
uv pip install -e .
```

##  Usage Examples

### Basic Server Management

**Start the MCP server:**
```bash
acp server start
# Output: Server started.
```

**Stop the MCP server:**
```bash
acp server stop
# Output: Server stopped.
```

**Initialize configuration:**
```bash
acp init
# Output:
# Copied config.adminmcp.json to /home/user/.config/adminmcp/config.adminmcp.json
# Created /home/user/.config/adminmcp/mcp_settings.json
# Configuration initialized.
```

### Testing with MCP Inspector

The easiest way to test the server is using the MCP Inspector:

```bash
mcp dev ./src/adminmcp/server/acp_server.py
```

This starts the MCP Inspector UI where you can interact with all available tools and resources.

### Programmatic Usage

The server can be used programmatically through MCP clients. Here are some example tool calls:

```python
# Mathematical operations
result = add(5, 3)  # Returns 8
result = multiply(4, 7)  # Returns 28

# Resource access
pi_value = get_constant("pi")  # Returns 3.141592653589793
is_even = is_even(42)  # Returns True

# DateTime information
current = current_datetime()
# Returns: {"datetime": "2024-01-01T12:00:00+00:00", "timezone": "UTC", "unix_timestamp": 1704110400.0}

# Wikipedia lookup
article = wikipedia_article("Python (programming language)")
# Returns article summary JSON
```

##  Configuration

AdminMCP uses a configuration system stored in `~/.config/adminmcp/`. The configuration is initialized automatically with the `acp init` command.

### Configuration Files

#### `config.adminmcp.json`
Template configuration file with default settings:

```json
{
    "application": {
        "config_folder": "~/.config/adminmcp",
        "log_folder": "~/.local/share/adminmcp/logs",
        "data_folder": "~/.local/share/adminmcp/data",
        "logging_level": "info"
    },
    "server": {
        "port": 8000
    },
    "client": {}
}
```

#### `mcp_settings.json`
Runtime configuration for MCP server settings:
…