A
licenseB
qualityF
maintenanceA server that uses the Model Context Protocol (MCP) to allow AI agents to safely execute shell commands on a host system.
1
234
9
MIT
No user-submitted related servers found.
Scored across 3 tools
Each tool has a clear, distinct purpose: reading spilled output, executing commands, and retrieving sandbox info. No overlap exists.
All tool names follow a consistent verb_noun pattern with snake_case: read_file_chunk, shell_exec, shell_info.
Three tools is on the low end but appropriate for a focused sandbox execution server. The scope is narrow yet complete enough.
Core operations (execute, read output, info) are covered, but missing features like managing spilled files, listing sandbox contents, or aborting commands represent notable gaps.