BS

blazickjp/shell-mcp-server

开发工具
22 stars 0 forks 质量 90 趋势 90

Secure shell command execution MCP server for Claude AI. Enables controlled shell access within specified directories.

概览

🚀 Add secure shell command execution capabilities to your AI applications with the Shell MCP Server! Built for the Model Context Protocol. - 🔒 - Commands run only in specified directories - 🐚 - Support for bash, sh, cmd, powershell - ⏱️ - Automatic termination of long-running commands - 🌍 - Works on both Unix and Windows systems - 🛡️ - Built-in directory and shell validation Add this to your Claude Desktop config to enable shell command execution: Configure behavior with command-line arguments: Environment variables: - COMMAND_TIMEOUT: ⏱️ Max execution time in seconds (default: 30) - 🔐 : Commands can only execute in specified directories - 🔒 : Only configured shells are allowed - ⏰ : All commands have a configurable timeout - 🛑 : Working directory validation prevents traversal attacks - 👤 : Commands run with the same permissions as the server process Contributions are welcome!

README

🖥️ Shell MCP Server

🚀 Add secure shell command execution capabilities to your AI applications with the Shell MCP Server! Built for the Model Context Protocol.

✨ Features

  • 🔒 Secure Execution - Commands run only in specified directories
  • 🐚 Multiple Shells - Support for bash, sh, cmd, powershell
  • ⏱️ Timeout Control - Automatic termination of long-running commands
  • 🌍 Cross-Platform - Works on both Unix and Windows systems
  • 🛡️ Safe by Default - Built-in directory and shell validation

🚀 Quick Start

Installation

# Using pip
pip install shell-mcp-server

# Using uv (recommended)
uv pip install shell-mcp-server

🔌 Claude Desktop Integration

Add this to your Claude Desktop config to enable shell command execution:

🎮 Usage Examples

Basic File Operations

# List directory contents
result = execute_command(
    command="ls -la",
    shell="bash",
    cwd="/path/to/project"
)

# Find files by pattern
result = execute_command(
    command="find . -name '*.py'",
    shell="bash",
    cwd="/path/to/project"
)

Project Management

# Git operations
result = execute_command(
    command="git status && git diff",
    shell="bash",
    cwd="/path/to/repo"
)

# Package management
result = execute_command(
    command="pip list --outdated",
    shell="bash",
    cwd="/path/to/python/project"
)

System Information

# Resource usage
result = execute_command(
    command="df -h && free -h",
    shell="bash",
    cwd="/path/to/dir"
)

# Process monitoring
result = execute_command(
    command="ps aux | grep python",
    shell="bash",
    cwd="/path/to/dir"
)

File Processing

# Search file content
result = execute_command(
    command="grep -r 'TODO' .",
    shell="bash",
    cwd="/path/to/project"
)

# File manipulation
result = execute_command(
    command="awk '{print $1}' data.csv | sort | uniq -c",
    shell="bash",
    cwd="/path/to/data"
)

Windows-Specific Examples

# List processes
result = execute_command(
    command="Get-Process | Where-Object {$_.CPU -gt 10}",
    shell="powershell",
    cwd="C:\\path\\to\\dir"
)

# System information
result = execute_command(
    command="systeminfo | findstr /B /C:'OS'",
    shell="cmd",
    cwd="C:\\path\\to\\dir"
)

⚙️ Configuration

Configure behavior with command-line arguments:

Argument Description
directories 📁 List of allowed directories
--shell name path 🐚 Shell specifications (name and path)

Environment variables:

  • COMMAND_TIMEOUT: ⏱️ Max execution time in seconds (default: 30)

🛡️ Security Features

  • 🔐 Directory Isolation: Commands can only execute in specified directories
  • 🔒 Shell Control: Only configured shells are allowed
  • ⏰ Timeout Protection: All commands have a configurable timeout
  • 🛑 Path Validation: Working directory validation prevents traversal attacks
  • 👤 Permission Isolation: Commands run with the same permissions as the server process

🛠️ Development

Set up your development environment:

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install development dependencies
uv pip install -e ".[test]"

# Run tests
python -m pytest

# Run tests with coverage
python -m pytest --cov=shell_mcp_server

🤝 Contributing

Contributions are welcome! Feel free to:

  • 🐛 Report bugs
  • 💡 Suggest features
  • 🔧 Submit pull requests
  • 📚 Improve documentation

📜 License

MIT License - see LICENSE for details.


View this README on GitHub

安装

This server does not publish a one-line install command.

Open the repository installation guide

配置

{ "mcpServers": { "shell-mcp-server": { "command": "uv", "args": [ "--directory", "/path/to/shell-mcp-server", "run", "shell-mcp-server", "/path/to/allowed/dir1", "/path/to/allowed/dir2", "--shell", "bash", "/bin/bash", "--shell", "zsh", "/bin/zsh" ] } } }