Integrations
Provides system command execution capabilities on macOS, with specific installation paths for the Claude Desktop app configuration on macOS systems.
Tools
Tools are for LLMs to request. Claude Sonnet 3.5 intelligently uses run_command
. And, initial testing shows promising results with Groq Desktop with MCP and llama4
models.
Currently, just one command to rule them all!
run_command
- run a command, i.e.hostname
orls -al
orecho "hello world"
etc- Returns
STDOUT
andSTDERR
as text - Optional
stdin
parameter means your LLM can- pass code in
stdin
to commands likefish
,bash
,zsh
,python
- create files with
cat >> foo/bar.txt
from the text instdin
- pass code in
- Returns
Warning
Be careful what you ask this server to run!
In Claude Desktop app, use Approve Once
(not Allow for This Chat
) so you can review each command, use Deny
if you don't trust the command.
Permissions are dictated by the user that runs the server.
DO NOT run with sudo
.
Video walkthrough
Prompts
Prompts are for users to include in chat history, i.e. via Zed
's slash commands (in its AI Chat panel)
run_command
- generate a prompt message with the command output
Development
Install dependencies:
Build the server:
For development with auto-rebuild:
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Groq Desktop (beta, macOS) uses ~/Library/Application Support/groq-desktop-app/settings.json
Use the published npm package
Published to npm as mcp-server-commands using this workflow
Use a local build (repo checkout)
Make sure to run npm run build
Logging
Claude Desktop app writes logs to ~/Library/Logs/Claude/mcp-server-mcp-server-commands.log
By default, only important messages are logged (i.e. errors).
If you want to see more messages, add --verbose
to the args
when configuring the server.
By the way, logs are written to STDERR
because that is what Claude Desktop routes to the log files.
In the future, I expect well formatted log messages to be written over the STDIO
transport to the MCP client (note: not Claude Desktop app).
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
You must be authenticated.
local-only server
The server can only run on the client's local machine because it depends on local resources.
An MCP server to run commands.
Related MCP Servers
- AsecurityAlicenseAqualityMCP server allowing any and all command execution over CMDLast updated -2339JavaScriptMIT License
- -securityFlicense-qualityA configurable MCP server that dynamically loads capabilities from a remote configuration to bridge MCP clients with remote APIs for executing actions, accessing resources, and utilizing prompt templates.Last updated -1,2614TypeScript
- -securityFlicense-qualityAn MCP server that allows AI assistants like Claude to execute terminal commands on the user's computer and return the output, functioning like a terminal through AI.Last updated -7Python
- -securityFlicense-qualityAn MCP server that allows AI models to execute system commands on local machines or remote hosts via SSH, supporting persistent sessions and environment variables.Last updated -91TypeScript