Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by kevinwatt • Analytics & Monitoring
A lightweight MCP server that lets LLM agents execute whitelisted shell commands securely with resource, timeout, and output size controls.
List and inspect files or directories on a host (e.g., using shell_ls, shell_pwd, shell_find) while ensuring only allowed flags are used.
Collect system status and diagnostics such as disk usage, memory usage, process lists, uptime, and hardware/network info (e.g., shell_df, shell_free, shell_ps, lspci, netstat).
Perform safe network or lookup operations like DNS queries and WHOIS lookups (e.g., dig, nslookup, whois) with controlled arguments and execution limits.
shell-mcp provides an MCP-compatible server that enables language models to run approved shell commands and arguments while enforcing safety constraints. It includes whitelisting of commands, CPU/memory monitoring, execution timeouts, and output size limits to reduce risk. The project is distributed as an npm package and integrates with MCP clients such as Dive Desktop and Claude.
List directory contents
Concatenate and display file contents
Show current working directory
Show disk usage
Display text
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.