Provides tools to check and kill Chrome instances with MCP profiles, allowing management of browser instances used by Claude.
Leverages native macOS confirmation dialogs for dangerous commands, providing secure command execution with system-level security verification.
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 foundTypeScript implementation
Works with npx for easy execution
Related MCP server: Command Executor MCP Server
Installation
Or use with npx (no installation required):
Configuration
Create a configuration file in your project root or home directory:
Project-specific config (highest priority):
<project>/.claude/.danger-zone-exec.local.jsonc(recommended for comments)<project>/.claude/.danger-zone-exec.local.json
Global config (fallback):
~/.claude/.danger-zone-exec.jsonc(recommended for comments)~/.claude/.danger-zone-exec.json
Usage with Claude Desktop / Claude Code
Add to your Claude configuration:
Note: When using Claude Code, the cwd is automatically set to your current project directory.
Development
Configuration Options
Command Properties
name: Tool name (used asexec_<name>)description: Description shown in Claudecommand: Shell command to executeargs: Optional array of default arguments
DangerZone Properties
name: Tool name (used asdanger_<name>)description: Description shown in Claudecommand: Shell command to executepreAuthorized: 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