server-run-commands
About
server-run-commands is an MCP (Model Context Protocol) server that lets an LLM execute commands on the local operating system. It is designed for developers who want to give a language model the ability to run shell commands and receive their output.
Explore
- Runs commands on the local OS
- Passes the process exit code back to the LLM
- Returns command stdout to the LLM
- Simple installation via npm and build step
- git clone https://github.com/anton-107/server-run-commands.git
- cd server-run-commands
- npm install
- npm run build
Add this to your claude_desktop_config.json:
```json
{
"mcpServers": {
"run-commands": {
"command": "<PATH TO LOCAL NODE>",
"args": [
"<PATH TO GIT CLONE FOLDER>/server-run-commands/build"
]
}
}
}
- run-command
- Run a command on the local OS
- Input: command (string)
- Passes the process exit code and stdout back to the LLM
Code written following the official MCP guide:
- https://modelcontextprotocol.io/quickstart
Tools
- run-command - Run a command on the local OS - Input:command (string)
- Passes the process exit code and stdout back to the LLM
Installation
-git clone https://github.com/anton-107/server-run-commands.git
- cd server-run-commands
- npm install
- npm run build
Usage with Claude Desktop
Add this to yourclaude_desktop_config.json:
```json
{
"mcpServers": {
"run-commands": {
"command": "<PATH TO LOCAL NODE>",
"args": [
"<PATH TO GIT CLONE FOLDER>/server-run-commands/build"
]
}
}
}Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
