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.
- 🔒 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
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.
execute_command: Run terminal commands securely (including SSH and remote commands)
- 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
# 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 buildTo publish the package:
- Copy
.npmrc.exampleto.npmrc - Add your npm authentication token to
.npmrc - Run
npm publish --access public
Note: Never commit your .npmrc file with the authentication token. It is already added to .gitignore.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'feat: Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
MIT License - see the LICENSE file for details.
For bug reports and feature requests, please open an issue.