Atlas / MCP servers / phialsbasement / Cmd

CmdSAFE

mcp/phialsbasement/cmd

MCP server for executing CMD commands. Can be hooked to claude for additional agentics.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 0r · 2w · 0d
Transport
stdio
License
MIT
Stars
24
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://smithery.ai/server/server-cmd) A Model Context Protocol (MCP) server implementation for executing CMD commands on both Windows and Linux, as well as allowing SSH connections. This server allows you to integrate command-line operations with MCP-compatible applications.

Features

  • Execute CMD commands through MCP
  • TypeScript implementation
  • Built on the official MCP SDK
  • Cross-platform compatibility

Installation

Installing via Smithery

To install CMD Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install server-cmd --client claude

Manual Installation

npm install server-cmd

Prerequisites

  • Node.js (v16 or higher recommended)
  • npm or yarn package manager

Usage

import { MCPCmdServer } from 'server-cmd';

// Initialize the server
const server = new MCPCmdServer();

// Start the server
server.start();

Configuration

The server can be configured through environment variables or a configuration object:

const config = {
// Add your configuration options here
};

const server = new MCPCmdServer(config);

Development

To set up the development environment:

  1. Clone the repository:
git clone https://github.com/PhialsBasement/CMD-MCP-Server.git
cd CMD-MCP-Server
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Scripts

  • npm run build - Compile TypeScript to JavaScript
  • npm run prepare - Prepare the package for publishing

Dependencies

  • @modelcontextprotocol/sdk: ^1.0.1
  • glob: ^10.3.10
  • zod-to-json-schema: ^3.23.5

#

Read from source at commit 5cb2980cd0e2OBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add server-cmd -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "server-cmd": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (2)

0 read · 2 write · 0 destructive.

ToolRiskDescription
execute_commandwriteExecute a command and return its output.
execute_ssh_commandwriteExecute a command on a remote server via SSH.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
glob, ssh2, zod-to-json-schema, @types/node, @types/ssh2, shx, ts-node, typescript
Why it matters. 8 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 5cb2980cd0e2full audit observations/trust-audit/mcp-server/phialsbasement__cmd.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-095cb2980cd0e2SAFEB89first audit
06

Questions

What is the Cmd MCP server?

MCP server for executing CMD commands. Can be hooked to claude for additional agentics.

What tools does Cmd expose?

2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Cmd safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Cmd need?

No credential environment variables were found in its source, so it appears to need none.

How does Cmd run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as server-cmd at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (5cb2980cd0e2), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement