mcpField
T
Terminal MCP Server

Terminal MCP Server

Local
github.com/stat-guyDeveloper Tools8Updated 98w ago

About Terminal MCP Server

Terminal MCP Server exposes terminal operations to Claude Desktop. It can run commands, retain the current directory between commands, and return output and exit codes.

Key features

  1. 01Executes commands with arguments
  2. 02Maintains directory state
  3. 03Reports terminal environment details
  4. 04Captures stdout, stderr, and exit codes
  5. 05Formats errors and handles timeouts

Use cases

  1. 01Inspect files in the current directory
  2. 02Run commands from Claude Desktop
  3. 03Change directories between commands
  4. 04Check shell and platform details

MCP support

Provides command execution, directory navigation, current-directory lookup, and terminal information tools to Claude Desktop through MCP.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Terminal MCP Server

A Model Context Protocol (MCP) server that enables execution of terminal commands through Claude Desktop.

Features

  • Execute any terminal command with arguments and options
  • Navigate between directories while maintaining state
  • Get terminal environment information
  • Full output capture (stdout, stderr, exit codes)
  • Proper error handling and formatting

Prerequisites

  • Node.js v18 or higher
  • TypeScript
  • Claude Desktop

Installation

  1. Clone the repository:
git clone https://github.com/stat-guy/terminal.git
cd terminal
  1. Install dependencies:
npm install
  1. Build the project:
npm run build

Local Development Setup

  1. Create or edit your Claude Desktop configuration file:

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

Add the following configuration:

{
  "mcpServers": {
    "terminal": {
      "command": "node",
      "args": [
        "[PATH_TO_REPO]/dist/index.js"
      ],
      "env": {
        "PERMISSION_REQUIRED": "true"
      }
    }
  }
}

Replace [PATH_TO_REPO] with the actual path to your cloned repository.

  1. Restart Claude Desktop

Available Tools

execute_command
  • Execute any terminal command
  • Supports command arguments and options
  • Captures full output and exit codes
change_directory
  • Change the current working directory
  • Maintains state between commands
  • Supports relative and absolute paths
get_current_directory
  • Get the current working directory path
get_terminal_info
  • Get information about the terminal environment
  • Shows shell, user, platform, and recent command history

Usage Examples

Ask Claude to execute terminal commands like:

Can you check what's in my current directory?
-> Executes: ls -la

Can you tell me the current directory?
-> Executes: pwd

Can you change to the Downloads folder?
-> Executes: cd ~/Downloads

Security Considerations

  • The server requires explicit user permission through Claude Desktop for command execution
  • Environment variables can be controlled through the configuration
  • Command execution includes timeouts and error handling

Development

  1. Watch for changes:
npm run watch
  1. Test changes:
  • Make changes to source files in src/
  • Rebuild using npm run build
  • Restart Claude Desktop to load changes

Project Structure

/
├── src/
│   └── index.ts    # Main server implementation
├── package.json    # Project configuration and dependencies
├── tsconfig.json  # TypeScript configuration
└── README.md      # This file

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.