Repository files navigation

Tools are for LLMs to request. Claude Sonnet 3.5 intelligently usesrun_command. And, initial testing shows promising results withGroq Desktop with MCP andllama4 models.

Currently, just one command to rule them all!

• run_command - run a command, i.e.hostname orls -al orecho "hello world" etc
  • ReturnsSTDOUT andSTDERR as text
  • Optionalstdin parameter means your LLM can
    • pass code instdin to commands likefish,bash,zsh,python
    • create files withcat >> foo/bar.txt from the text instdin

Prompts are for users to include in chat history, i.e. viaZed's slash commands (in its AI Chat panel)

• run_command - generate a prompt message with the command output

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

To use with Claude Desktop, add the server config:

On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json

Groq Desktop (beta, macOS) uses~/Library/Application Support/groq-desktop-app/settings.json

Published to npm asmcp-server-commands using thisworkflow

{"mcpServers": {"mcp-server-commands": {"command":"npx","args": ["mcp-server-commands"]    }  }}

Make sure to runnpm run build

{"mcpServers": {"mcp-server-commands": {// works b/c of shebang in index.js"command":"/path/to/mcp-server-commands/build/index.js"    }  }}

• Most models are trained such that they don't think they can run commands for you.
  • Sometimes, they use tools w/o hesitation... other times, I have to coax them.
  • Use a system prompt or prompt template to instruct that they should follow user requests. Including to userun_commands without double checking.
• Ollama is a great way to run a model locally (w/ Open-WebUI)

# NOTE: make sure to review variants and sizes, so the model fits in your VRAM to perform well!# Probably the best so far is [OpenHands LM](https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model)ollama pull https://huggingface.co/lmstudio-community/openhands-lm-32b-v0.1-GGUF# https://ollama.com/library/devstralollama pull devstral# Qwen2.5-Coder has tool use but you have to coax itollama pull qwen2.5-coder

The server is implemented with theSTDIO transport.ForHTTP, usemcpo for anOpenAPI compatible web server interface.This works withOpen-WebUI

uvx mcpo --port 3010 --api-key"supersecret" -- npx mcp-server-commands# uvx runs mcpo => mcpo run npx => npx runs mcp-server-commands# then, mcpo bridges STDIO <=> HTTP

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 theargs when configuring the server.

By the way, logs are written toSTDERR because that is what Claude Desktop routes to the log files.In the future, I expect well formatted log messages to be written over theSTDIO transport to the MCP client (note: not Claude Desktop app).

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.