Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

shell-mcp-server

MCP.Pizza Chef: blazickjp

The shell-mcp-server is a secure MCP server designed to enable controlled shell command execution within AI applications, such as those using Claude AI. It supports multiple shell environments including bash, sh, cmd, and powershell, and enforces execution only within specified directories to ensure safety. The server includes features like automatic timeout for long-running commands and cross-platform compatibility for Unix and Windows systems. Its built-in validation mechanisms make it safe by default, providing a robust solution for integrating shell capabilities into AI workflows while maintaining strict security controls.

Use This MCP server To

Execute shell commands securely within AI workflows Run scripts in controlled directories for automation Integrate shell access in Claude AI applications Manage cross-platform shell tasks from AI agents Enforce timeout on long-running shell commands Support multiple shell types in AI environments

README

🖥️ Shell MCP Server

PyPI version License: MIT Python Code style: black

🚀 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:

📝 Click to view configuration
{
    "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"
            ]
        }
    }
}

🎮 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.


🌟 Enhance Your AI with Secure Shell Access! 🌟

Built for the Model Context Protocol | Made with ❤️ by the MCP Community

🎉 Star us on GitHub!
If you find this tool useful, consider giving it a star! It helps others discover the project.

shell-mcp-server FAQ

How does shell-mcp-server ensure command execution security?
It restricts command execution to specified directories and validates shell types to prevent unauthorized access.
Can shell-mcp-server run on both Windows and Unix systems?
Yes, it is designed to be cross-platform, supporting Unix shells like bash and sh, as well as Windows cmd and powershell.
What happens if a shell command runs too long?
The server includes timeout control that automatically terminates commands exceeding the configured duration.
Which shells are supported by shell-mcp-server?
It supports bash, sh, cmd, and powershell shells, allowing flexible integration across different environments.
Is shell-mcp-server compatible with LLMs other than Claude AI?
While optimized for Claude AI, it can be integrated with other LLM providers like OpenAI and Gemini through MCP protocol.
How do I install shell-mcp-server?
Installation is straightforward via PyPI using pip, compatible with Python 3.11 and above.
Does shell-mcp-server provide any built-in safety features?
Yes, it includes directory and shell validation to ensure safe command execution by default.
Can I customize the allowed directories for command execution?
Yes, you can configure which directories the server permits for running shell commands.