MCP Command Server

A secure Model Context Protocol (MCP) server for executing system commands through LLM applications like Claude.

Quick Start

Install the package:

uv pip install mcp-command-server

Configure allowed commands:

export ALLOWED_COMMANDS="ls,pwd,echo"

Add to Claude Desktop configuration:

{
  "mcpServers": {
    "command-server": {
      "command": "uv",
      "args": ["run", "python", "-m", "mcp_command_server"],
      "env": {
        "ALLOWED_COMMANDS": "ls,pwd,echo"
      }
    }
  }
}

Features

🔒 Secure command execution with whitelist
✅ User confirmation for all commands
📝 Comprehensive audit logging
🔍 Input validation and sanitization
🤖 Claude Desktop integration

Documentation

For complete documentation, see the docs/ directory:

Development

Setup

# Clone repository
git clone https://github.com/yourusername/mcp-command-server.git
cd mcp-command-server

# Create virtual environment
uv venv
source .venv/bin/activate  # On Unix/macOS
.venv\Scripts\activate     # On Windows

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

Testing

# Run all tests
pytest

# Run specific test file
pytest tests/unit/security/test_validator.py

# Run with coverage
pytest --cov=mcp_command_server

Contributing

Fork the repository
Create your feature branch
Run tests and linting
Submit a pull request

License

MIT License - see LICENSE for details.

mcp-command-server