@Zelaron
Basic information
MCP server enabling AI assistants to execute terminal commands through a secure shell interface
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Pandoras-Shell": {
"command": "python3",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Execute any shell command and return its output
An MCP server that empowers AI assistants to execute terminal commands on your system with full access. It is compatible with any AI assistant supporting the Model Context Protocol, with setup instructions tailored for Claude Desktop.
Install prerequisites (Python 3.10+, Git, uv), clone the repository, create a virtual environment, install dependencies, and then configure the claude_desktop_config.json file with the correct paths to the executor script. After restarting Claude Desktop, the server appears in the Installed MCP Servers list.
pwd to determine the current working directoryNo. This server grants AI assistants unrestricted ability to execute terminal commands with your user privileges. **Only use in controlled environments like virtual machines (VMs) or development systems you can afford to rebuild. Never use on production systems or machines with sensitive data.**
Python 3.10 or higher, Git, and `uv` for package management. Claude Desktop with an active Claude Pro/Enterprise subscription is used for the configuration example.
Create or edit `claude_desktop_config.json` in the correct configuration directory (e.g., `%APPDATA%\Claude\` on Windows or `~/Library/Application Support/Claude/` on macOS). Set the `command` to the Python interpreter inside your virtual environment and `args` to the executor script path, with `PYTHONPATH` set to the `src` directory.
Restart Claude Desktop completely, then click the 🔌 icon to check if "pandoras-shell" appears in the Installed MCP Servers list. If not, inspect the MCP logs (e.g., `%APPDATA%\Claude\Logs\mcp*.log` on Windows).
The server sets a 5-minute timeout for command execution. If the timeout is reached, the command is terminated and error handling is applied.
The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
Open-source Mac network diagnostics for AI agents and humans. Check connectivity, Wi-Fi, hotspots and traffic from the terminal or MCP.
Most MCP servers hand your agent documentation. This one hands it a renderer. Write a single React Native codebase that ships native AR to phones and VR to headsets, then let your agent validate every prop, check each pl
Comments