Command Executor MCP server

This MCP server allows you to execute pre-approved commands securely through the Model Context Protocol. It provides a safe way to run commands from AI assistants with strict validation and security measures in place.

Installation and Setup

Installing the Command Executor

To install the command-executor MCP server:

npm install

After installation, build the server:

npm run build

If you're developing and want auto-rebuilding when files change:

npm run watch

Configuration Options

Allowed Commands

By default, the server allows these commands:

• git
• ls
• mkdir
• cd
• npm
• npx
• python

You can customize the allowed commands by setting an environment variable:

export ALLOWED_COMMANDS=git,ls,mkdir,python

Claude Desktop Integration

To use this server with Claude Desktop, add it to your Claude configuration file:

MacOS location:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows location:

%APPDATA%/Claude/claude_desktop_config.json

Configuration example:

{
  "mcpServers": {
    "command-executor": {
      "command": "/path/to/command-executor/build/index.js"
    }
  }
}

Usage Guide

Using the Execute Command Tool

The server provides a single tool called execute_command that runs pre-approved commands securely.

Parameters:

• command (string, required): The command to execute

Example Request:

{
  "name": "execute_command",
  "arguments": {
    "command": "git status"
  }
}

Example Response:

{
  "content": [
    {
      "type": "text",
      "text": "On branch main\nNothing to commit, working tree clean"
    }
  ]
}

Error Responses

If a command is not allowed or fails to execute, you'll receive an error response:

{
  "content": [
    {
      "type": "text",
      "text": "Command execution failed: Command not allowed"
    }
  ],
  "isError": true
}

Security Features

Command Security

The server implements several security measures:

• Pre-approved Command List: Only explicitly allowed commands can be executed
• Command Validation: Command prefix validation prevents command injection
• No Shell Execution: Commands aren't passed to a shell, improving security
• Environment Isolation: Server runs in its own environment with controlled variables

Debugging

Since MCP servers communicate over stdio, you can use the MCP Inspector for debugging:

npm run inspector

This will provide a URL to access debugging tools in your browser.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "command-executor" '{"command":"/path/to/command-executor/build/index.js"}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "command-executor": {
            "command": "/path/to/command-executor/build/index.js"
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "command-executor": {
            "command": "/path/to/command-executor/build/index.js"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect