MCP Terminal Server

A secure command-line interface server for the Model Context Protocol (MCP) that enables AI models to interact with your terminal while maintaining security and control.

Features

• 🔒 Secure command execution with configurable permissions
• 📁 File system operations within allowed paths
• 🌍 Environment variable management
• 💻 Cross-platform support (Windows, macOS, Linux)
• 🔌 Remote system connections support via command execution

Available Tools

• execute_command: Run terminal commands securely (including SSH and remote commands)

Security

• All operations are restricted to specified allowed paths
• Commands are validated and sanitized before execution
• Environment variables are carefully managed
• Proper error handling for security-related issues

Development

# Clone the repository
git clone https://github.com/dillip285/mcp-terminal.git

# Install dependencies
npm install

# Configure npm authentication
cp .npmrc.example .npmrc
# Edit .npmrc and add your NPM_TOKEN

# Run tests
npm test

# Build the project
npm run build

Publishing

To publish the package:

1. Copy .npmrc.example to .npmrc
2. Add your npm authentication token to .npmrc
3. Run npm publish --access public

Note: Never commit your .npmrc file with the authentication token. It is already added to .gitignore.

Related Projects

• Model Context Protocol
• Claude Desktop

Support

For bug reports and feature requests, please open an issue.

Usage with Claude Desktop

Add the server configuration to your Claude Desktop config file:

{
  "mcpServers": {
    "terminal": {
      "command": "npx",
      "args": [
        "@dillip285/mcp-terminal",
        "--allowed-paths",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Restart Claude Desktop to apply the changes. You can now use the terminal capabilities through Claude with secure file access and command execution.

License

MIT License - see the LICENSE file for details.