DesktopCommander MCP Server

What does “DesktopCommander” MCP Server do?

DesktopCommander MCP Server is a Model Context Protocol (MCP) server designed to augment AI assistants like Claude by granting them powerful capabilities for interacting directly with a user’s desktop environment. Specifically, it provides terminal control, file system search, and diff-based file editing. By exposing these functionalities through the MCP interface, DesktopCommander enables AI-driven workflows that can execute shell commands, browse and manipulate files, and make precise edits. This significantly enhances development productivity, allowing for tasks such as automating local operations, performing advanced searches, and editing code or documents directly from within an AI assistant. The server is especially suited for developers seeking to bridge the gap between conversational AI and hands-on desktop automation.

List of Prompts

(No explicit prompt templates found in the repository files or documentation.)

List of Resources

(No specific MCP resources are detailed or exposed in the available repository documentation.)

List of Tools

• Terminal Control: Enables the AI assistant to execute commands in the user’s shell environment, allowing automation and scripting of system tasks.
• File System Search: Provides the ability to search files and directories for specific content or metadata, facilitating codebase exploration and information retrieval.
• Diff File Editing: Allows the AI to perform line-by-line edits on files using diff patches, enabling automated refactoring, bug fixes, or content updates.

Use Cases of this MCP Server

• Automated Script Execution: Developers can instruct the AI to run shell commands or scripts, streamlining repetitive or complex operations directly from chat.
• Codebase Exploration: Quickly search and navigate large file systems or codebases, allowing for fast location of files, functions, or specific code snippets.
• Automated File Editing: Apply precise changes to files using AI-generated diffs, supporting tasks like refactoring, formatting, or applying bug fixes.
• Configuration Management: AI can modify environment or application configuration files, assisting with setup and onboarding processes.
• System Diagnostics: Gather logs, check process statuses, or diagnose issues by leveraging terminal access and file reading capabilities.

How to set it up

Windsurf

1. Ensure you have Node.js installed on your system.
2. Locate your Windsurf configuration file (typically windsurf.config.json).
3. Add the DesktopCommander MCP server to the mcpServers section of your configuration:

   {
     "mcpServers": {
       "desktopcommander": {
         "command": "npx",
         "args": ["@desktopcommander/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration file and restart Windsurf.
5. Verify the setup by checking that DesktopCommander appears in your available MCP servers.

Claude

1. Install Node.js if not already present.
2. In the Claude server environment, locate the configuration file or method for adding MCP servers.
3. Include DesktopCommander MCP using the following format:

   {
     "mcpServers": {
       "desktopcommander": {
         "command": "npx",
         "args": ["@desktopcommander/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart the Claude server.
5. Confirm the connection by running a test command via Claude.

Cursor

1. Install Node.js as a prerequisite.
2. Find Cursor’s configuration file (for example, cursor.config.json).
3. Add the MCP server entry:

   {
     "mcpServers": {
       "desktopcommander": {
         "command": "npx",
         "args": ["@desktopcommander/mcp-server@latest"]
       }
     }
   }
   

4. Save changes and restart Cursor.
5. Check for DesktopCommander MCP server in the connected tools list.

Cline

1. Ensure Node.js is set up.
2. Open your Cline configuration file.
3. Insert DesktopCommander MCP server details as:

   {
     "mcpServers": {
       "desktopcommander": {
         "command": "npx",
         "args": ["@desktopcommander/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Validate the server connection by executing a simple file search or terminal command.

Securing API Keys

To securely provide API keys or sensitive credentials:

• Use environment variables in your configuration files. Example:

{
  "mcpServers": {
    "desktopcommander": {
      "command": "npx",
      "args": ["@desktopcommander/mcp-server@latest"],
      "env": {
        "API_KEY": "${API_KEY}"
      },
      "inputs": {
        "apiKey": "${API_KEY}"
      }
    }
  }
}

Replace ${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:

{
  "desktopcommander": {
    "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 “desktopcommander” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: Not specified

Based on the available documentation, DesktopCommander MCP provides powerful direct desktop interaction, but lacks documented prompt templates and resources, and does not specify Roots or Sampling support. It scores very high on practical utility and open-source adoption.

MCP Score