execute-commandLABSCO SUMMARY
The approval dialog is the product.
Plenty of servers will run a shell command for a model; the interesting part here is that each one surfaces as a growl notification carrying the command text and the working directory, so you see what is about to happen rather than reading it in a log afterwards. That makes it usable on a machine you actually care about, at the cost of a prompt every time.
What it is
A stdio server that lets a model run shell commands on your machine, but puts a permission dialog in front of every one of them. The notification shows the command and the working directory it will run in, so approving is a decision rather than a reflex.
What you get
execute-commandruns a shell command after you approve it in the notificationsystem-inforeturns OS, uptime, memory, disk and CPU- Each permission dialog names the command and the directory it will run in
- Timeout limits stop a runaway process, and input is sanitised against command injection
Requirements
Build it from the repository: npm install then npm run build (package perm-shell-mcp, version 0.1.0). Point your client at node with the path to dist/index.js. No account and no key — but it runs commands as you, on your machine, so the notification is the only thing between the model and your shell.
Setup effort
Build from source — git clone https://github.com/mcollina/perm-shell-mcp.git
USE CASES
01
Letting an assistant poke around your filesystem
Ask it to list or inspect files and approve each command as it comes up.
02
Answering questions about the machine itself
Get OS, uptime, memory, disk and CPU back in one call instead of scripting it.
03
Running a build or a test suite on request
Hand the command to the model but keep the go/no-go decision, with the working directory shown in the dialog.
2 tools
Listed in project docs. Your client may show a different list.
system-infoBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
# Clone the repository
git clone https://github.com/mcollina/perm-shell-mcp.git
cd perm-shell-mcp
# Install dependencies
npm install
# Build the project
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"permshell": {
"command": "node",
"args": [
"<YOUR_PATH_TO_PERM_SHELL_MCP>/dist/index.js"
]
}
}
}
