{"type":"mcp_server","name":"mcp-server-commands","description":"This repository provides tools, `run_command` and `run_script`, for LLMs like Claude to execute commands and scripts, enabling creative interactions while requiring careful user oversight for security. This repository provides tools,","category":"Developer Tools","language":"JavaScript","stars":228,"forks":16,"owner":"g0t4","github_url":"https://github.com/g0t4/mcp-server-commands","homepage":null,"setup":"## Setup\n\nTo use with Claude Desktop, add the server config:\n\nOn MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\nOn Windows: `%APPDATA%/Claude/claude_desktop_config.json`\n\n### Use the published npm package\n\nPublished to npm as [mcp-server-commands](https://www.npmjs.com/package/mcp-server-commands) using this [workflow](https://github.com/g0t4/mcp-server-commands/actions)\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-server-commands\": {\n      \"command\": \"npx\",\n      \"args\": [\"mcp-server-commands\"]\n    }\n  }\n}\n```\n\n### Use a local build (repo checkout)\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-server-commands\": {\n      // works b/c of shebang in index.js\n      \"command\": \"/path/to/mcp-server-commands/build/index.js\"\n    }\n  }\n}\n```\n\n### Logging\n\nClaude Desktop app writes logs to `~/Library/Logs/Claude/mcp-server-mcp-server-commands.log`\n\nBy default, only important messages are logged (i.e. errors).\nIf you want to see more messages, add `--verbose` to the `args` when configuring the server.\n\nBy the way, logs are written to `STDERR` because that is what Claude Desktop routes to the log files.\nIn the future, I expect well formatted log messages to be written over the `STDIO` transport to the MCP client (note: not Claude Desktop app).\n\n### Debugging\n\nSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:\n\n```bash\nnpm run inspector\n```\n\nThe Inspector will provide a URL to access debugging tools in your browser.","tools":"## Available Tools\n\n1.  `run_command` (run a command, i.e. `hostname` or `ls -al` or `echo \"hello world\"` etc, returns STDOUT and STDERR as text)\n2.  `run_script` (run a script! (i.e. `fish`, `bash`, `zsh`, `python`), script is passed over STDIN, `run_script` == `run_command` + script over STDIN)","faq":null,"created_at":"2024-11-29T02:39:02+00:00","updated_at":"2025-03-27T16:09:39+00:00","source_url":"https://model-context-protocol.com/servers/llm-command-script-execution-server","related_articles":[]}