MCPs
mcp-server-commands

mcp-server-commands

Expose safe shell command execution as an MCP server for LLM tooling.

View on GitHub

207

Stars

Forks

207

Watchers

Issues

mcp-server-commands exposes a server that provides a 'run_command' tool for local or remote large language models (LLMs) via the Model Context Protocol (MCP). It enables LLMs to execute shell commands, retrieve STDOUT and STDERR, and optionally pass data through stdin. The tool integrates with apps like Claude Desktop and Groq Desktop, and can be run via npm or as a local build, with security in mind.

Key Features

Implements MCP server for command execution

Supports 'run_command' with stdin/stdout/stderr handling

Integrates with Claude Desktop and Groq Desktop

NPM package and local build support

User approval warnings for sensitive commands

Optional verbose logging

Works with local LLMs and prompt engineering

Compatible with HTTP/OpenAPI via mcpo bridge

Recommends usage with safe user permissions

Single-command interface for simplicity

Use Cases

Enable LLMs to execute validated shell commands in a controlled environment

Integrate command execution tools into Claude Desktop conversational flows

Facilitate tool use for LLMs running locally or via Open-WebUI

Provide safe automation for developer environments via model chat interfaces

Bridge MCP tools to HTTP/OpenAPI endpoints for broader service integration

Support AI assistant workflows requiring real-time OS or file system interactions

Enable prompt-based command execution in chat applications

Centralize command execution for AI-driven coding agents

Enhance local AI model usability by augmenting with system command abilities

Streamline the addition of custom shell automations for AI models

README

Tools

Tools are for LLMs to request. Claude Sonnet 3.5 intelligently uses run_command. And, initial testing shows promising results with Groq Desktop with MCP and llama4 models.

Currently, just one command to rule them all!

run_command - run a command, i.e. hostname or ls -al or echo "hello world" etc
- Returns STDOUT and STDERR as text
- Optional stdin parameter means your LLM can
  - pass code in stdin to commands like fish, bash, zsh, python
  - create files with cat >> foo/bar.txt from the text in stdin

[!WARNING] Be careful what you ask this server to run! In Claude Desktop app, use Approve Once (not Allow for This Chat) so you can review each command, use Deny if you don't trust the command. Permissions are dictated by the user that runs the server. DO NOT run with sudo.

Video walkthrough

Prompts

Prompts are for users to include in chat history, i.e. via Zed's slash commands (in its AI Chat panel)

run_command - generate a prompt message with the command output

Development

Install dependencies:

bash

npm install

Build the server:

bash

npm run build

For development with auto-rebuild:

bash

npm run watch

Installation

To use with Claude Desktop, add the server config:

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

Groq Desktop (beta, macOS) uses ~/Library/Application Support/groq-desktop-app/settings.json

Use the published npm package

Published to npm as mcp-server-commands using this workflow

json

{
  "mcpServers": {
    "mcp-server-commands": {
      "command": "npx",
      "args": ["mcp-server-commands"]
    }
  }
}

Use a local build (repo checkout)

Make sure to run npm run build

json

{
  "mcpServers": {
    "mcp-server-commands": {
      // works b/c of shebang in index.js
      "command": "/path/to/mcp-server-commands/build/index.js"
    }
  }
}

Local Models

Most models are trained such that they don't think they can run commands for you.
- Sometimes, they use tools w/o hesitation... other times, I have to coax them.
- Use a system prompt or prompt template to instruct that they should follow user requests. Including to use run_commands without double checking.
Ollama is a great way to run a model locally (w/ Open-WebUI)

# NOTE: make sure to review variants and sizes, so the model fits in your VRAM to perform well!

# Probably the best so far is [OpenHands LM](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model)
ollama pull https://huggingface.co/lmstudio-community/openhands-lm-32b-v0.1-GGUF

# https://ollama.com/library/devstral
ollama pull devstral

# Qwen2.5-Coder has tool use but you have to coax it
ollama pull qwen2.5-coder

HTTP / OpenAPI

The server is implemented with the STDIO transport. For HTTP, use mcpo for an OpenAPI compatible web server interface. This works with Open-WebUI

bash

uvx mcpo --port 3010 --api-key "supersecret" -- npx mcp-server-commands

# uvx runs mcpo => mcpo run npx => npx runs mcp-server-commands
# then, mcpo bridges STDIO <=> HTTP

[!WARNING] I briefly used mcpo with open-webui, make sure to vet it for security concerns.

Logging

Claude Desktop app writes logs to ~/Library/Logs/Claude/mcp-server-mcp-server-commands.log

By default, only important messages are logged (i.e. errors). If you want to see more messages, add --verbose to the args when configuring the server.

By the way, logs are written to STDERR because that is what Claude Desktop routes to the log files. In the future, I expect well formatted log messages to be written over the STDIO transport to the MCP client (note: not Claude Desktop app).

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

bash

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Star History

Repository Owner

g0t4

User

Repository Details

Language TypeScript

Default Branch master

Size 207 KB

Contributors 1

License MIT License

MCP Verified Nov 11, 2025

Programming Languages

TypeScript

74.33%

JavaScript

22.56%

Shell

3.11%

Related MCPs

Discover similar Model Context Protocol servers

MCP Shell Server

A secure, configurable shell command execution server implementing the Model Context Protocol.

MCP Shell Server provides secure remote execution of whitelisted shell commands via the Model Context Protocol (MCP). It supports standard input, command output retrieval, and enforces strict safety checks on command operations. The tool allows configuration of allowed commands and execution timeouts, and can be integrated with platforms such as Claude.app and Smithery. With robust security assessments and flexible deployment methods, it facilitates controlled shell access for AI agents.

⭐ 153
MCP
tumf/mcp-shell-server

SSH MCP Server

MCP-compliant SSH server for secure command execution on Linux and Windows.

SSH MCP Server provides an MCP-compliant interface to expose SSH control for both Linux and Windows systems. It enables secure execution of shell commands remotely, supporting password and SSH key authentication as well as sudo and su elevation. Built with TypeScript and the official MCP SDK, the server offers configurable timeouts, process management, and compatibility with popular LLM clients such as Claude Desktop and Cursor. Designed for robust and flexible integration, it facilitates natural language interfaces to system administration tasks.

⭐ 137
MCP
tufantunc/ssh-mcp

CMD MCP Server

Execute CMD commands via the Model Context Protocol with cross-platform and SSH support.

CMD MCP Server is an implementation of the Model Context Protocol (MCP) for executing CMD commands on Windows and Linux systems, with additional support for SSH connections. It enables seamless integration of command-line operations with MCP-compatible applications, leveraging the official MCP SDK. Written in TypeScript for cross-platform compatibility, it allows programmatic execution, configuration, and extension of CMD operations through standardized protocols. The server is designed for easy installation, robust configuration, and developer-friendly extension.

⭐ 22
MCP
PhialsBasement/CMD-MCP-Server

CLI MCP Server

A secure MCP server for controlled command-line operations.

CLI MCP Server provides a secure implementation of the Model Context Protocol (MCP) for executing command-line operations with robust security features. It enables controlled CLI access by enforcing command and flag whitelisting, path validation, and shell operator restrictions, making it suitable for integration with large language model applications. Designed for configurable deployment, it supports detailed error reporting, execution timeouts, and strict working directory controls.

⭐ 155
MCP
MladenSU/cli-mcp-server

mcp-shell

A secure Model Context Protocol (MCP) server for AI-driven shell command execution.

mcp-shell enables AI assistants and MCP clients to securely execute shell commands via the standardized Model Context Protocol. Built in Go and leveraging the official MCP SDK, it facilitates structured, auditable, and context-aware access to shell environments. The server emphasizes security through Docker isolation, command validation, resource limits, and comprehensive audit logging.

⭐ 44
MCP
sonirico/mcp-shell

mcp-server-docker

Natural language management of Docker containers via Model Context Protocol.

mcp-server-docker enables users to manage Docker containers using natural language instructions through the Model Context Protocol. It allows composing, introspecting, and debugging containers, as well as managing persistent Docker volumes. The tool is suitable for server administrators, tinkerers, and AI enthusiasts looking to leverage LLM capabilities for Docker management. Integration with tools like Claude Desktop and Docker ensures flexible deployment and easy connectivity to Docker engines.

⭐ 648
MCP
ckreiling/mcp-server-docker

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

mcp-server-commands

Key Features

Use Cases

README

Tools

Video walkthrough

Prompts

Development

Installation

Use the published npm package

Use a local build (repo checkout)

Local Models

HTTP / OpenAPI

Logging

Debugging

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs