MoLing MCP server

MoLing is a Model Context Protocol (MCP) server that enables system interactions through operating system APIs. It allows file operations, command execution, and browser control without requiring additional dependencies. The tool serves as a local office automation assistant that works directly with compatible MCP clients like Claude, Cline, and Cherry Studio.

Installation

Option 1: Install via Script

For Linux/MacOS:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/gojue/moling/HEAD/install/install.sh)"

For Windows:

powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/gojue/moling/HEAD/install/install.ps1 | iex"

Option 2: Direct Download

1. Download the installation package from the releases page
2. Extract the package
3. Run the server:

./moling

Option 3: Build from Source

1. Clone the repository:

git clone https://github.com/gojue/moling.git
cd moling

2. Build the project (requires Golang toolchain):

make build

3. Run the compiled binary:

./bin/moling

Configuration

MoLing Server Configuration

The configuration file will be generated at /Users/username/.moling/config/config.json, which you can modify as needed. If the file does not exist, create it using:

moling config --init

MCP Client Configuration

To configure Claude as a client, add the following configuration to the Claude config path (~/Library/Application\ Support/Claude/claude_desktop_config):

{
  "mcpServers": {
    "MoLing": {
      "command": "/usr/local/bin/moling",
      "args": []
    }
  }
}

Replace /usr/local/bin/moling with the actual path to the MoLing binary on your system.

Automatic Client Configuration

You can automatically install the configuration for supported MCP clients by running:

moling client --install

MoLing will detect compatible MCP clients (including Cline, Claude, Roo Code) and install the configuration for you.

Features

• File System Operations: Read, write, merge, analyze, and aggregate files
• Command Execution: Run system commands directly
• Browser Control: Automated browser interactions powered by chromedp
• Multiple Operation Modes:
  • Stdio Mode: CLI-based interactive mode for user-friendly experience
  • SSR Mode: Server-Side Rendering mode for headless/automated environments

Usage

Once the server is started, you can connect to it using any supported MCP client by configuring the client to point to your MoLing server address. MoLing supports multiple operating systems including Windows, Linux, and macOS, though it has been most extensively tested on macOS.

Supported MCP Clients

• Claude
• Cline
• Cherry Studio
• Any other client that supports the MCP protocol

Caution

Command-line operations can be dangerous. Use with care, especially when executing system commands through the MCP interface.

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.