mcpField
S
Script Tool

Script Tool

Local
github.com/nguyenvanduocitDeveloper Tools0Updated 33w ago

About Script Tool

Script Tool is an MCP server and standalone CLI for executing command-line scripts. It supports configurable interpreters, execution timeouts, and captured output and errors.

Key features

  1. 01Execute scripts through MCP
  2. 02Select an interpreter
  3. 03Timeout protection
  4. 04Capture output and errors
  5. 05Standalone CLI

Use cases

  1. 01Run a shell command
  2. 02Execute Python with a chosen interpreter
  3. 03Run a script in a working directory

MCP support

Exposes safe command-line script execution to MCP clients, including interpreter selection, timeout handling, and output capture. A standalone CLI is also available without an MCP client.

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

Script Tool

A tool for executing command line scripts through MCP.

Features

  • Execute command line scripts safely
  • Support for different interpreters
  • Timeout protection
  • Output and error capture
  • Cross-platform support (Linux, macOS, Windows)

Installation

There are several ways to install the Script Tool:

Option 1: Download from GitHub Releases
  1. Visit the GitHub Releases page
  2. Download the binary for your platform:
    • script-mcp_linux_amd64` for Linux
    • script-mcp_darwin_amd64 for macOS
    • script-mcp_windows_amd64.exe for Windows
  3. Make the binary executable (Linux/macOS):
    chmod +x script-mcp_*
    
  4. Move it to your PATH (Linux/macOS):
    sudo mv script-mcp_* /usr/local/bin/script-mcp@latest
    
Option 2: Go install
go install github.com/nguyenvanduocit/script-mcp

Config

Claude
{
  "mcpServers": {
    "script": {
      "command": "/path-to/script-mcp"
    }
  }
}

CLI Usage

In addition to the MCP server, script-mcp ships a standalone CLI binary (script-cli) for direct terminal use — no MCP client needed.

Installation
just install-cli
# or
go install github.com/nguyenvanduocit/script-mcp/cmd/script-cli@latest
Quick Start

No credentials required. The CLI executes scripts locally.

script-cli execute --content "echo Hello, World!"
Commands
CommandDescription
execute (or exec, run)Safely execute a script with timeout
Examples
# Run a shell command
script-cli execute --content "ls -la"

# Run with a specific interpreter
script-cli execute --content "print('Hello')" --interpreter /usr/bin/python3

# Run with a working directory
script-cli execute --content "pwd" --working-dir /tmp

# Run a multi-line script
script-cli execute --content "#!/bin/bash
echo 'Starting...'
date
echo 'Done'"

# JSON output (captures stdout/stderr separately)
script-cli exec --content "echo hello" --output json
Flags
FlagDescription
--contentScript content to execute (required)
--interpreterInterpreter path (default: /bin/sh)
--working-dirWorking directory for execution
--envPath to .env file
--outputOutput format: text (default) or json

Note: Scripts time out after 30 seconds.

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Installation

Homebrew (macOS/Linux)
brew install nguyenvanduocit/tap/script-mcp

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.