cmd-line-executor MCP server
About
Experimental MCP server to execute command line commands
Details
- Author
- MarkusPfundstein
- GitHub stars
- 4
- Downloads
- 193
- Categories
- Other
Jump to
- Single tool run_command for executing command-line commands
- Accepts command and arguments as separate strings
- Returns stdout, stderr, status code from the command
- Built with Python and the uv package manager
- Supports both development and published deployment modes
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
cmd-line-executor MCP serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via the Claude Desktop configuration file (claude_desktop_config.json) using either the development path with uv or the published path with uvx. The server exposes one tool run_command that accepts a cmd string and an args string array.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"cmd-line-executor mcp server": {
"cmd-line-executor-MCP": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"cmd-line-executor-MCP": {
"command": "uv",
"args": [
"sync"
]
}
}cmd-line-executor MCP server
Example MCP server to call command line apps
Components
Tools
The server implements one tool:
- run_command: Runs a command line comment
- Takes "cmd" and "args" as string arguments
- Runs the command and returns stdout, stderr, status_code, etc.
Configuration
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
<details>
<summary>Development/Unpublished Servers Configuration</summary>
"mcpServers": {
"cmd-line-executor": {
"command": "uv",
"args": [
"--directory",
"/Users/$(whoami)/experiments/claude-mvp/cmd-line-executor",
"run",
"cmd-line-executor"
]
}
}
</details>
<details>
<summary>Published Servers Configuration</summary>
"mcpServers": {
"cmd-line-executor": {
"command": "uvx",
"args": [
"cmd-line-executor"
]
}
}
</details>
Development
Building and Publishing
To prepare the package for distribution:
1. Sync dependencies and update lockfile:
uv sync
2. Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
3. Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token: --token or UV_PUBLISH_TOKEN
- Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/markus/experiments/claude-mvp/cmd-line-executor run cmd-line-executor
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
