概览
What is server-run-commands?
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.
How to use server-run-commands?
Clone the repository, then run npm install and npm run build to compile the server. To use it with Claude Desktop, add an entry to claude_desktop_config.json specifying the path to Node.js and the build folder. The server exposes a single tool called run-command that accepts a command (string) input.
Key features of server-run-commands
- 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
Use cases of server-run-commands
- Execute a command and capture its output for the LLM
- Trigger local scripts or utilities from an AI assistant
FAQ from server-run-commands
How do I install server-run-commands?
Clone the repository with git clone https://github.com/anton-107/server-run-commands.git, run cd server-run-commands && npm install && npm run build.
How do I configure server-run-commands with Claude Desktop?
Add a run-commands entry in your claude_desktop_config.json with command pointing to a local Node.js executable and args containing the path to the server-run-commands build folder.
What tools does server-run-commands provide?
It provides one tool: run-command, which runs a command on the local OS.
What input does the run-command tool expect?
The tool expects a single string input named command.
What dependencies does server-run-commands require?
It requires Node.js and npm to build and run the server.
