EarthlingAI/command
If you are the rightful owner of command and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This repository contains a Model Context Protocol (MCP) server implementation for executing commands, allowing MCP-compatible AI assistants to execute commands in specified directories.
The Model Context Protocol (MCP) is an open standard developed by Anthropic that enables secure, two-way connections between data sources and AI-powered tools. This MCP server provides a universal tool called 'command' that allows AI agents to execute commands in specified directories. The server is designed to expose data and functionality to AI applications, enabling them to intelligently retrieve, process, and leverage information across private data sources. The server is structured to include configuration files, core server functionality, tool implementations, utility functions, and scripts for running and building. It is compatible with Claude, an AI assistant, and requires configuration to specify allowed directories for command execution. The server includes security measures to restrict command execution to specified directories and recommends using a dedicated user with limited permissions.
Features
- Universal command execution tool for AI agents
- Secure, two-way connections between data sources and AI tools
- Configurable directory access for command execution
- Compatibility with Claude AI assistant
- Security measures to restrict unauthorized access
Usages
usage with Claude on Unix
{
"mcpServers": {
"command": {
"command": "/path/to/command/start-server.sh",
"args": [
"/path/to/allowed/directory1",
"/path/to/allowed/directory2",
"/path/to/allowed/directory3"
]
}
}
}usage with Claude on Windows
{
"mcpServers": {
"command": {
"command": "C:\\path\\to\\command\\start-server.bat",
"args": [
"C:\\path\\to\\allowed\\directory1",
"C:\\path\\to\\allowed\\directory2",
"C:\\path\\to\\allowed\\directory3"
]
}
}
}Tools
command
Execute commands in a specified directory
