Cmd Line Executor MCP

A server example project for invoking command-line tools via the MCP protocol

Developer tools Operating system automation #Command-line tools #MCP protocol #Process invocation .Python

rating : 2.5 points

downloads : 6

update time : 2025-04-29

What is Command Line Executor?

This is a server based on the Model Context Protocol (MCP) that allows you to execute various command-line programs through a standard interface. It encapsulates complex command-line operations into simple API calls, making it particularly suitable for scenarios where commands need to be executed automatically.

How to use Command Line Executor?

You can connect to this server by configuring the Claude Desktop client and then use simple JSON format requests to execute commands. The server will return the complete results of the command execution, including the output content and status code.

Applicable scenarios

Suitable for scenarios that require automatic execution of system commands, batch processing of files, running scripts, etc. For example: file conversion, data processing, system monitoring and other tasks.

Main features

Execute command lineExecute any command-line program by specifying the command and parameters, and obtain the complete execution result

Advantages and limitations

Advantages

Simplify the command-line operation process

Standardize the command execution interface

Can be integrated into automated workflows

Limitations

Only supports command-line programs

Requires pre-configuration of the server

Security depends on system permission settings

How to use

Installation and configuration

Add server configuration to the Claude Desktop configuration file and choose different configuration methods according to the development or production environment

Start the server

Use the uv or uvx command to start the server, depending on your environment

Send a request

Send a JSON format request via the MCP protocol, including the command and parameters to be executed

Usage examples

List directory contentsUse the ls command to view files and folders in the current directory

Run a Python scriptExecute a Python data processing script

Frequently Asked Questions

How to debug the server?

Which operating systems does the server support?

How to publish an update?

Related resources

MCP Inspector tool

A visualization tool for debugging MCP servers

PyPI Publishing Guide

Official documentation for Python package publishing

🚀 Command Line Executor MCP Server

An example MCP server for invoking command-line applications

✨ Features

Tools

This server implements one tool:

run_command: Run a command-line instruction
- Accepts "cmd" and "args" as string parameters.
- Runs the command and returns information such as stdout, stderr, and status_code.

📚 Documentation

Configuration

[The original text has no specific content for this part, so it is skipped according to the rules.]

🚀 Quick Start

Installation

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

Development/Unreleased Server Configuration

``` "mcpServers": { "cmd-line-executor": { "command": "uv", "args": [ "--directory", "/Users/$(whoami)/experiments/claude-mvp/cmd-line-executor", "run", "cmd-line-executor" ] } } ```

Released Server Configuration

``` "mcpServers": { "cmd-line-executor": { "command": "uvx", "args": [ "cmd-line-executor" ] } } ```

🔧 Technical Details

Building and Publishing

To prepare the distribution package:

Synchronize dependencies and update the lock file:

uv sync

Build the package distribution:

uv build

This will create source code and wheel distributions in the dist/ directory.

Publish to PyPI:

uv publish

Note: You need to set PyPI credentials via environment variables or command-line flags:

Token: --token or UV_PUBLISH_TOKEN
Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs through standard input and output, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP inspector by executing the following command via npm:

npx @modelcontextprotocol/inspector uv --directory /Users/markus/experiments/claude-mvp/cmd-line-executor run cmd-line-executor

After starting, the inspector will display a URL that you can access in your browser to start debugging.

Featured MCP Services

Notion Api MCP

Certified

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

Python

145

4.5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

569

5 points

Figma Context MCP

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

757

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご