Terminal MCP server

The MCP Terminal Server provides a secure command-line interface for the Model Context Protocol (MCP), allowing AI models to interact with your terminal while maintaining robust security controls. This server enables models like Claude to execute commands and access files within carefully defined boundaries.

Installation and Setup

To use the MCP Terminal Server with Claude Desktop, you need to add the server configuration to your Claude Desktop configuration file:

1. Open your Claude Desktop config file
2. Add the server configuration in the following format:

{
  "mcpServers": {
    "terminal": {
      "command": "npx",
      "args": [
        "@dillip285/mcp-terminal",
        "--allowed-paths",
        "/path/to/allowed/directory"
      ]
    }
  }
}

3. Replace /path/to/allowed/directory with the actual directory path you want to give Claude access to
4. Save the config file and restart Claude Desktop

The server will be automatically downloaded and installed through npx when Claude Desktop runs the command.

Configuration Options

Allowed Paths

The --allowed-paths argument is crucial for security as it restricts file system operations to specified directories:

"args": [
  "@dillip285/mcp-terminal",
  "--allowed-paths",
  "/path/to/allowed/directory1,/path/to/allowed/directory2"
]

Multiple directories can be specified by separating them with commas.

Using Terminal Capabilities

Once configured, you can ask Claude to perform terminal operations. The server provides the following capabilities:

Executing Commands

Claude can run terminal commands within the security boundaries you've defined. Examples of requests you might make:

• "List files in my project directory"
• "Run a git status on my repository"
• "Show me the contents of config.json"

Secure File System Operations

The server allows Claude to:

• Read files within allowed paths
• Write to files within allowed paths
• List directory contents
• Create directories

All operations are restricted to the paths you specified in the configuration.

Security Features

The MCP Terminal Server implements several security measures:

• Path Restriction: All file operations are confined to specified allowed paths
• Command Validation: Commands are sanitized before execution
• Environment Variable Protection: Careful management of environment variables
• Cross-Platform Security: Works safely on Windows, macOS, and Linux

Supported Platforms

The server works on:

• Windows
• macOS
• Linux

Each platform has appropriate security controls for its specific environment.

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.