Super Shell MCP server for AI agents

Super Shell MCP is a protocol server that allows secure execution of shell commands across multiple platforms (Windows, macOS, Linux) with built-in security features like command whitelisting and approval workflows.

Installation

Via Smithery

The easiest way to install Super Shell MCP Server for Claude Desktop is via Smithery:

npx -y @smithery/cli install @cfdude/super-shell-mcp --client claude

Manually

# Clone the repository
git clone https://github.com/cfdude/super-shell-mcp.git
cd super-shell-mcp

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Using NPX (Recommended)

For Roo Code

"super-shell": {
  "command": "npx",
  "args": [
    "-y",
    "super-shell-mcp"
  ],
  "alwaysAllow": [],
  "disabled": false
}

For Claude Desktop

"super-shell": {
  "command": "npx",
  "args": [
    "-y",
    "super-shell-mcp"
  ],
  "alwaysAllow": false,
  "disabled": false
}

Using Local Installation

For Roo Code

"super-shell": {
  "command": "node",
  "args": [
    "/path/to/super-shell-mcp/build/index.js"
  ],
  "alwaysAllow": [],
  "disabled": false
}

For Claude Desktop

"super-shell": {
  "command": "node",
  "args": [
    "/path/to/super-shell-mcp/build/index.js"
  ],
  "alwaysAllow": false,
  "disabled": false
}

Specifying a Custom Shell

"super-shell": {
  "command": "node",
  "args": [
    "/path/to/super-shell-mcp/build/index.js",
    "--shell=/usr/bin/bash"
  ],
  "alwaysAllow": [],
  "disabled": false
}

Windows 11 Example

"super-shell": {
  "command": "C:\\Program Files\\nodejs\\node.exe",
  "args": [
    "C:\\Program Files\\nodejs\\node_modules\\npm\\bin\\npx-cli.js",
    "-y",
    "super-shell-mcp",
    "C:\\Users\\username"
  ],
  "alwaysAllow": [],
  "disabled": false
}

Platform-Specific Configuration Paths

Windows

Roo Code: %APPDATA%\Code\User\globalStorage\rooveterinaryinc.roo-cline\settings\cline_mcp_settings.json
Claude Desktop: %APPDATA%\Claude\claude_desktop_config.json

macOS

Roo Code: ~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json

Linux

Roo Code: ~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json
Claude Desktop: ~/.config/Claude/claude_desktop_config.json

Available Tools

Get Platform Information

{
  "tool": "get_platform_info",
  "parameters": {}
}

Execute Command

{
  "tool": "execute_command",
  "parameters": {
    "command": "ls",
    "args": ["-la"]
  }
}

Whitelist Management

Get Whitelist

{
  "tool": "get_whitelist",
  "parameters": {}
}

Add to Whitelist

{
  "tool": "add_to_whitelist",
  "parameters": {
    "command": "python3",
    "securityLevel": "safe",
    "description": "Run Python 3 scripts"
  }
}

Update Security Level

{
  "tool": "update_security_level",
  "parameters": {
    "command": "python3",
    "securityLevel": "requires_approval"
  }
}

Remove from Whitelist

{
  "tool": "remove_from_whitelist",
  "parameters": {
    "command": "python3"
  }
}

Command Approval Workflow

Get Pending Commands

{
  "tool": "get_pending_commands",
  "parameters": {}
}

Approve Command

{
  "tool": "approve_command",
  "parameters": {
    "commandId": "command-uuid-here"
  }
}

Deny Command

{
  "tool": "deny_command",
  "parameters": {
    "commandId": "command-uuid-here",
    "reason": "This command is potentially dangerous"
  }
}

Default Whitelisted Commands

Safe Commands (All Platforms)

echo - Print text to standard output

Unix-like Safe Commands (macOS/Linux)

ls - List directory contents
pwd - Print working directory
cat - Concatenate and print files
grep - Search for patterns in files
find - Find files in a directory hierarchy
cd - Change directory
head - Output the first part of files
tail - Output the last part of files
wc - Print newline, word, and byte counts

Windows-specific Safe Commands

dir - List directory contents
type - Display the contents of a text file
findstr - Search for strings in files
where - Locate programs
whoami - Display current user
hostname - Display computer name
ver - Display operating system version

Troubleshooting

Windows-Specific Issues

PowerShell Script Execution Policy: Run PowerShell as Administrator and execute Set-ExecutionPolicy RemoteSigned
Path Separators: Use double backslashes (\\) in JSON configuration
Command Not Found: Use Windows equivalents (dir instead of ls, findstr instead of grep)

macOS/Linux-Specific Issues

Shell Permissions: Ensure the shell has appropriate permissions with chmod +x /path/to/shell
Environment Variables: Set environment variables in the shell's profile file

Logging System

Logs are stored in logs/super-shell-mcp.log
View logs with: tail -f logs/super-shell-mcp.log

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.