cmd-line-executor MCP server

What is cmd-line-executor MCP server?

An example MCP server that calls command line applications, providing a tool to run commands and return their output.

How to use cmd-line-executor MCP server?

Install via the Claude Desktop configuration file (claude_desktop_config.json) using either the development path with uv or the published path with uvx. The server exposes one tool run_command that accepts a cmd string and an args string array.

Key features of cmd-line-executor MCP server

• Single tool run_command for executing command-line commands
• Accepts command and arguments as separate strings
• Returns stdout, stderr, status code from the command
• Built with Python and the uv package manager
• Supports both development and published deployment modes

Use cases of cmd-line-executor MCP server

• Run shell commands from an MCP client (e.g., Claude Desktop)
• Execute system utilities and capture their output
• Automate command-line tasks within an MCP workflow

FAQ from cmd-line-executor MCP server

What does the run_command tool return?

It returns stdout, stderr, and status_code from the executed command.

What runtime does cmd-line-executor MCP server require?

It requires Python and the uv package manager. The published version is distributed via PyPI.

How do I configure cmd-line-executor MCP server for Claude Desktop?

Edit your claude_desktop_config.json (found at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, or %APPDATA%/Claude/claude_desktop_config.json on Windows) and add the server configuration under mcpServers using either a local development path with uv or the published uvx command.

How can I debug cmd-line-executor MCP server?

Use the MCP Inspector by running npx @modelcontextprotocol/inspector uv --directory <path> run cmd-line-executor. The Inspector provides a browser-based debugging interface.

How do I publish my own version of this server?

Build the package with uv build, then publish to PyPI using uv publish. You need to set PyPI credentials via token or username/password.