mcp-server-commands MCP Server

What does “mcp-server-commands” MCP Server do?

The mcp-server-commands MCP (Model Context Protocol) Server acts as a bridge between AI assistants and the ability to execute local or system commands securely. By exposing an interface for running shell commands, it allows AI clients to access external data, interact with the file system, perform diagnostics, or automate workflows directly from their environment. The server processes command requests from LLMs and returns the output, including both STDOUT and STDERR, which can be used for further analysis or actions. This enhances development workflows by enabling tasks such as listing directories, viewing system information, or running scripts, thereby expanding the practical capabilities of AI assistants for developers and power users.

List of Prompts

• run_command – Generate a prompt message with the command output.

List of Resources

No explicit resources are listed in the available documentation or code.

List of Tools

• run_command – Runs a specified command (e.g., hostname, ls -al, echo "hello world"). Returns STDOUT and STDERR as text. Supports an optional stdin parameter to pass input (such as code or file contents) to commands that accept it, facilitating scripting and file operations.

Use Cases of this MCP Server

• System Diagnostics: Run commands like hostname or top to fetch system status or environment details directly from within the AI assistant.
• File Management: List directories (ls -al), create or read files, and manipulate text files using shell commands.
• Script Execution: Execute scripts or code snippets (e.g., Python, Bash) by passing them via stdin, enabling rapid prototyping or automation.
• Development Automation: Automate repetitive tasks such as pulling code, building projects, or running tests via shell commands issued by the AI.
• Secure Command Approval: Integrate with tools like Claude Desktop to ensure that each command is reviewed and approved before execution, minimizing security risks.

How to set it up

Windsurf

1. Ensure Node.js and npm are installed.
2. Install the mcp-server-commands package:

   npm install -g mcp-server-commands
   

3. Edit your Windsurf configuration file to add the MCP server.
4. Add the following JSON snippet:

   {
     "mcpServers": {
       "mcp-server-commands": {
         "command": "npx",
         "args": ["mcp-server-commands"]
       }
     }
   }
   

5. Save the configuration and restart Windsurf.
6. Verify the server is running and accessible.

Claude

1. Make sure Node.js and npm are installed.
2. Install mcp-server-commands globally:

   npm install -g mcp-server-commands
   

3. Locate your Claude Desktop config file:
   • MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Add:

   {
     "mcpServers": {
       "mcp-server-commands": {
         "command": "npx",
         "args": ["mcp-server-commands"]
       }
     }
   }
   

5. Save and restart Claude Desktop.
6. Confirm the MCP server appears and is functional.

Cursor

1. Install Node.js and npm if required.
2. Globally install mcp-server-commands:

   npm install -g mcp-server-commands
   

3. Open your Cursor configuration file.
4. Insert:

   {
     "mcpServers": {
       "mcp-server-commands": {
         "command": "npx",
         "args": ["mcp-server-commands"]
       }
     }
   }
   

5. Save changes and restart Cursor.
6. Check that the MCP server is available for use.

Cline

1. Ensure Node.js/npm are installed.
2. Install the MCP server package:

   npm install -g mcp-server-commands
   

3. Edit the Cline MCP server configuration.
4. Add:

   {
     "mcpServers": {
       "mcp-server-commands": {
         "command": "npx",
         "args": ["mcp-server-commands"]
       }
     }
   }
   

5. Save and restart Cline.
6. Verify connectivity to the MCP server.

Securing API Keys

If you need to supply sensitive environment variables (e.g., API keys), use the env and inputs fields in your configuration:

{
  "mcpServers": {
    "mcp-server-commands": {
      "command": "npx",
      "args": ["mcp-server-commands"],
      "env": {
        "EXAMPLE_API_KEY": "${EXAMPLE_API_KEY}"
      },
      "inputs": {
        "apiKey": "${EXAMPLE_API_KEY}"
      }
    }
  }
}

Replace EXAMPLE_API_KEY with your actual environment variable name.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-server-commands": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-server-commands” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion:
This MCP server is simple but highly effective for its purpose: giving LLMs access to the system shell in a controlled way. It is well-documented, easy to configure, and has clear security warnings. However, its scope is limited (one tool, no explicit resources or prompt templates beyond run_command), and advanced MCP features like Roots and Sampling are not referenced in the documentation or code. Overall, it is well-suited for developers looking for shell access through AI, but lacks broader extensibility.

MCP Score