-
securityF
license-
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 -
7
Python
The mcp-server-commands server allows LLMs to execute system commands and scripts on the host machine, enabling interaction with the local environment.
- Execute Commands: Run shell commands (e.g.,
hostname,ls,echo) using therun_commandmethod, which returnsSTDOUTandSTDERR - Input Support: Provide input to commands via
stdinparameter for interactive programs likebashorpython - Run Scripts: Execute scripts by piping them to a specified interpreter (bash, python, etc.)
- Working Directory: Specify the working directory for command and script execution
- Integration with LLMs: Designed for use with models like Claude Sonnet 3.5, with command review capabilities in the Claude Desktop app
- Development Tools: Includes debugging and logging features such as the MCP Inspector
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.hostnameorls -alorecho "hello world"etc- Returns
STDOUTandSTDERRas text - Optional
stdinparameter means your LLM can- pass code in
stdinto commands likefish,bash,zsh,python - create files with
cat >> foo/bar.txtfrom 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
- -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
MCP-YNU FastMCP Serverofficial
-securityAlicense-qualityA dynamic MCP server implementation that automatically loads tools, resources, and prompts from their respective directories, allowing for easy extension and configuration.Last updated -PythonMIT License- PythonMIT License