"Shell" matching MCP servers:

AI-native SSH orchestration server enabling Claude or any MCP agent to execute commands, manage files, tunnels, and fleet operations across multiple hosts with security policies and audit logs.

Converts plain-language storage requests into validated Hitachi raidcom command lines and multi-step shell scripts, including ready-made provisioning recipes, command lookup, and model limit checks. It is build-only: it never connects to a storage system, runs a command, or holds credentials, returning reviewed command text for a person to execute.

Provides DSL diagnosis and CLI access to DrayTek Vigor 167 modems via interactive SSH shell, enabling command discovery and execution through MCP tools.

Enables AI-assisted remote server diagnostics by auto-executing known read-only commands and routing high-risk changes to a real human for approval through DingTalk interactive cards. It uses structured argv instead of shell strings, default-deny policy, and HMAC-signed agent execution with hash-chained auditing so the model never holds SSH keys or approval power.

MCP server enabling local network interaction, shell command execution, system resource monitoring, and SSH-based remote device management.

Enables local LLM clients to capture and analyze network traffic using Wireshark's CLI tools, providing packet summaries, protocol hierarchies, conversations, endpoints, expert info, and stream reassembly without shell access.

Enables AI agents to run shell and sudo commands on remote machines through profile-driven SSH sessions, with explicit target guards that prevent commands from hitting the wrong host. It offers bucketed inventory lookup, connectivity diagnostics, keepalive-based connection resilience, and credential-safe configuration management.

Enables AI agents to run ProjectDiscovery reconnaissance tools — subdomain discovery, DNS resolution, HTTP probing, port scanning, crawling, template scanning, and chained bounty workflows — through MCP under alternate tool names, so the underlying binary names never appear in the tool catalog. Includes confirm gates for intrusive scans and no-shell argument-array spawning.

Enables AI agents to access Zabbix monitoring, MeshCentral inventory and admin shell execution, and read-only Express Accounting data through role-separated MCP endpoints secured by token-based RBAC.

Enables agents to discover Jellyfin servers, authenticate as a restricted user to list libraries and search media, and import new files through a companion native plugin with resumable, SHA-256-verified uploads. Read-only for existing content, with no delete, overwrite, or arbitrary filesystem and shell tools.