Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by odysseus0 • Tools & CLI
An MCP server that lets LLM agents execute shell commands on the host and receive combined stdout/stderr and return codes.
Run arbitrary shell commands and obtain combined stdout/stderr and the process return code.
Inspect and manipulate local files and directories (for example, listing files or showing README contents).
Check installed tooling or environment information (for example, checking Python version or current system date).
This Model Context Protocol (MCP) server exposes a single tool to execute shell commands and return their output and exit status. It is installable via pip or run directly with uv/uvx and includes configuration examples for Claude.app and Zed. It is useful for agents that need to query the filesystem, check system tools, or run ad-hoc shell commands from within an LLM environment. The README also highlights security considerations and warns that commands run directly on the host.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.