π
windows-terminal-mcp
MCP server allowing LLMs to execute commands on Windows terminals, including local shells (cmd, PowerShell, bash) and remote SSH connections with a 3-level security model.
0 installs
Trust: 34 β Low
Security
Ask AI about windows-terminal-mcp
Powered by Claude Β· Grounded in docs
I know everything about windows-terminal-mcp. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Loading tools...
Reviews
Documentation
terminal-mcp
An MCP (Model Context Protocol) server that lets any LLM execute commands on a local terminal or over SSH β works on Windows and macOS.
- Run commands via native shells (
cmd/powershell/bashon Windows,zsh/bash/shon macOS) - Execute remote commands over SSH with key-based authentication
- 3-level security model: safe / confirm / blocked
Requirements
- Python 3.11+
- Claude Desktop or any MCP-compatible client
Installation
git clone https://github.com/marttinm/windows-terminal-mcp.git
cd windows-terminal-mcp
pip install -e .
Configure Claude Desktop
macOS
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"terminal": {
"command": "python3",
"args": ["-m", "terminal_mcp.server"]
}
}
}
Windows
Edit %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"terminal": {
"command": "cmd",
"args": ["/c", "python", "-m", "terminal_mcp.server"]
}
}
}
Restart Claude Desktop after saving the config.
Security
Commands fall into three categories:
| Level | Behavior | Examples |
|---|---|---|
| Safe | Executed directly | ls, git, npm, python, curl |
| Dangerous | Claude warns before executing | rm, rmdir, launchctl, diskutil |
| Blocked | Always rejected | rm -rf /, format, shutdown, mkfs |
License
MIT β see LICENSE
