Skip to main content
Glama

Danger Zone MCP

by koinunopochi
MIT License
0
  • Apple

Danger Zone MCP

A Model Context Protocol (MCP) server that allows executing predefined commands with safety checks.

Features

  • Execute safe commands from configuration

  • Execute dangerous commands with native macOS confirmation dialog

  • Support for pre-authorized dangerous commands (skip confirmation)

  • JSONC support (JSON with comments)

  • Multiple configuration file formats supported (.jsonc and .json)

  • Fallback to global config in ~/.claude/ if project config not found

  • TypeScript implementation

  • Works with npx for easy execution

Installation

npm install -g @koinunopochi/danger-zone-mcp

Or use with npx (no installation required):

npx @koinunopochi/danger-zone-mcp

Configuration

Create a configuration file in your project root or home directory:

  1. Project-specific config (highest priority):

    • <project>/.claude/.danger-zone-exec.local.jsonc (recommended for comments)

    • <project>/.claude/.danger-zone-exec.local.json

  2. Global config (fallback):

    • ~/.claude/.danger-zone-exec.jsonc (recommended for comments)

    • ~/.claude/.danger-zone-exec.json

{ // Safe commands that can be executed without confirmation "commands": [ { "name": "build_project", "description": "Build the project", "command": "npm", "args": ["run", "build"] }, { "name": "check_chrome_mcp", "description": "Check if MCP Chrome profile instances are running", "command": "ps aux | grep -E '(Google Chrome.*mcp-chrome-profile)' | grep -v grep | wc -l" } ], // Dangerous commands that require confirmation "dangerZone": [ { "name": "clean_build", "description": "Clean all build artifacts", "command": "rm -rf dist" // Will show confirmation dialog (default behavior) }, { "name": "kill_chrome_mcp", "description": "Kill all Chrome instances with MCP profile", "command": "pkill -f 'Google Chrome.*mcp-chrome-profile'", "preAuthorized": true // Skip confirmation dialog } ] }

Usage with Claude Desktop / Claude Code

Add to your Claude configuration:

{ "mcpServers": { "danger-zone": { "command": "npx", "args": ["@koinunopochi/danger-zone-mcp"] } } }

Note: When using Claude Code, the cwd is automatically set to your current project directory.

Development

# Install dependencies npm install # Build npm run build # Run in development mode npm run dev

Configuration Options

Command Properties

  • name: Tool name (used as exec_<name>)

  • description: Description shown in Claude

  • command: Shell command to execute

  • args: Optional array of default arguments

DangerZone Properties

  • name: Tool name (used as danger_<name>)

  • description: Description shown in Claude

  • command: Shell command to execute

  • preAuthorized: Skip confirmation dialog if true (optional, defaults to false)

Safety Features

  • Dangerous commands show native macOS confirmation dialog by default

  • Pre-authorized commands can skip confirmation when explicitly configured

  • Commands are sandboxed to configured list

  • Clear separation between safe and dangerous operations

Deploy Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

A Model Context Protocol server that enables safe execution of predefined commands with built-in safety checks, separating regular commands from dangerous operations requiring confirmation.

  1. Features
    1. Installation
      1. Configuration
        1. Usage with Claude Desktop / Claude Code
          1. Development
            1. Configuration Options
              1. Command Properties
              2. DangerZone Properties
            2. Safety Features

              Related MCP Servers

              • -
                security
                F
                license
                -
                quality
                A Model Context Protocol server that allows LLMs to execute shell commands and receive their output in a controlled manner.
                Last updated -
                3
              • A
                security
                F
                license
                A
                quality
                A Model Context Protocol server that allows secure execution of pre-approved commands, enabling AI assistants to safely interact with the user's system.
                Last updated -
                1
                2
                21
              • -
                security
                A
                license
                -
                quality
                A Model Context Protocol server that enables seamless execution of commands, Python code, web content fetching, and reusable task management with secure credentials handling.
              • A
                security
                F
                license
                A
                quality
                A Model Context Protocol server implementation that enables secure remote command execution via SSH, with features for managing and using SSH credentials.
                Last updated -
                5
                1
                9

              View all related MCP servers

              MCP directory API

              We provide all the information about MCP servers via our MCP API.

              curl -X GET 'https://glama.ai/api/mcp/v1/servers/koinunopochi/danger-zone-mcp'

              If you have feedback or need assistance with the MCP directory API, please join our Discord server