Atlas / MCP servers / xkiranj / Linux Command

Linux CommandSAFE

mcp/xkiranj/linux-command

MCP server and client for running Linux commands

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 0r · 1w · 0d
Transport
stdio
License
MIT
Stars
25
01

Overview

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

Overview

Linux Command MCP is a remote command execution system built using the Model Context Protocol (MCP), allowing secure and standardized execution of Linux commands.

Configuration for Claude Desktop MCP Servers

Understanding the Configuration

The MCP servers are configured in the claude_desktop_config.json file, typically located at ~/.config/Claude/claude_desktop_config.json.

Configuration Structure

"mcpServers": {
"server-name": {
"command": "node|npx|uvx",
"args": ["server-specific-arguments"],
"env": {
"OPTIONAL_ENVIRONMENT_VARIABLES": "value"
}
}
}

Linux Command MCP Server Configuration

"linux-command": {
"command": "node",
"args": [
"/full/path/to/linux-command-mcp/server/dist/index.js"
]
}

Configuration Explained

  • "command": Specifies the executor (node, npx, uvx)
  • "args": Full path to the server's executable
  • Ensure the path is an absolute path to your index.js

Important Configuration Tips

  • Always use full, absolute paths
  • Verify file permissions
  • Ensure the specified file is executable

Prerequisites

  • Node.js (v18.x or later)
  • npm
  • PM2 (for process management)

Installation

  1. Clone the repository
git clone 
cd linux-command-mcp
  1. Install server dependencies
cd server
npm install
npm run build
  1. Install client dependencies
cd ../client
npm install
npm run build

Usage

Starting the Server

  1. Navigate to the server directory
cd server
  1. Start with PM2
npm run pm2:start

Using the Client

Available Commands:

  1. exec - Execute a Linux command
  2. list [directory] - List directory contents
  3. help - Show this help
  4. exit - Exit the client

Execute commands directly:

# In the client directory
npm start 
exec "ls -l"
exec "list /home"
exec "uname -
Read from source at commit 50500110806eOBSERVED · 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 linux-command-mcp-server -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "linux-command-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (1)

0 read · 1 write · 0 destructive.

ToolRiskDescription
execute-commandwrite
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 (2)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
client/package.json
@modelcontextprotocol/sdk, zod, @types/node, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
server/package.json
@modelcontextprotocol/sdk, zod, @types/node, typescript
Why it matters. 4 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 50500110806efull audit observations/trust-audit/mcp-server/xkiranj__linux-command.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
2026-10-0950500110806eSAFEB89first audit
06

Questions

What is the Linux Command MCP server?

MCP server and client for running Linux commands

What tools does Linux Command expose?

1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Linux Command 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 Linux Command need?

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

How does Linux Command run?

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

How current is this page?

The grade is for one exact copy of the source (50500110806e), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement