About server-run-commands
A small MCP server that runs a command on the local operating system. It returns the process exit code and standard output to an LLM.
Key features
- 01Run a local OS command
- 02Return process exit code
- 03Return command standard output
Use cases
- 01Run a command through an MCP client
- 02Inspect command output from an LLM
- 03Check whether a local process succeeded
MCP support
Exposes a run-command tool to MCP clients for executing commands on the local OS and returning the exit code and standard output.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEserver-run-commands
MCP server to run commands on the local OS
Code written following the official MCP guide:
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.gitcd server-run-commandsnpm installnpm run build
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"run-commands": {
"command": "<PATH TO LOCAL NODE>",
"args": [
"<PATH TO GIT CLONE FOLDER>/server-run-commands/build"
]
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.