Local Command

Executes shell commands locally and returns structured outputs for MCP clients.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-kentaro_mcp-local-command-server": {
      "command": "/path/to/mcp-local-command-server/build/index.js",
      "args": []
    }
  }
}

This MCP server runs commands locally and returns structured outputs, enabling you to build interactive tools that harness your system’s capabilities. It is useful for automating tasks, integrating with clients, and exposing command results in a clean, programmatic format.

How to use

You interact with the server from an MCP client by invoking the available tool to execute shell commands on your machine. The server runs the command you specify, captures the output and exit status, and returns a structured result that your client can parse and present. This enables automation, debugging aids, and custom workflows that rely on real-time command execution.

How to install

Prerequisites you need before installing this MCP server are Node.js and npm. Ensure you have a working development environment with access to the command line.

Install dependencies for the MCP server:

npm install

Build the server to produce the runtime artifacts:

npm run build

For development with automatic rebuilds, start the watcher to rebuild on changes:

npm run watch

To configure the server for Claude Desktop, place the following JSON in the indicated path on your system. This registers the local MCP server so the client can connect to it.

{
  "mcpServers": {
    "local-command-server": {
      "command": "/path/to/mcp-local-command-server/build/index.js"
    }
  }
}

Notes

Debugging MCP servers that communicate over stdio can be challenging. You can use the MCP Inspector, a helper tool provided as a script during development. Run it to obtain a debugging URL you can open in a browser to inspect runtime behavior and outputs.

npm run inspector

Available tools

execute_command

Executes a shell command and returns a structured result including stdout, stderr, and exit status.