"Search for HITL (Human-in-the-Loop or other possible acronyms)" matching MCP servers:

Enforces mandatory human approval before LLM agents can edit files, create files, or execute shell commands, using session tokens and audit logging.

Enables AI coding agents to run one-shot commands and copy single files to and from remote servers through The Bastion, which authenticates, authorizes, and records each action. Access is controlled by the bastion rather than allowlists or deny lists.

Unofficial Powershell MCP server

Enables an AI agent to operate a spare Android phone through MCP: capture screenshots, inspect UI controls, tap/swipe, input Chinese text, launch apps, and optionally run rooted shell commands or transfer files. It also supports a live web console for remote viewing and control.

Self-hosted MCP coding server and unified local Control Center for ChatGPT web, enabling file editing, command execution, Git operations, and optional upstream MCP tools with conversation access controls.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.

Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around. MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.

AI-native security research platform that integrates Claude with MCP to execute real offensive security tools in an isolated Docker container, enabling natural language-driven recon, CVE scanning, Active Directory enumeration, and cryptographic posture assessment.

Enables LLM agents to remotely access a NAS physical serial console as an emergency recovery channel via Cloudflare Zero Trust, allowing commands, special keys, and reset operations even when the device is otherwise unreachable.

An MCP (Multi-Agent Conversation Protocol) server that enables interaction with Google's Managed Service for Microsoft Active Directory through its OpenAPI, allowing users to manage identity resources through natural language.

Exposes persistent, stateful remote Bash sessions to AI agents via SSH, enabling command execution with preserved working directory and environment.

An MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.

An MCP server that provides tools to interact with CLI applications, enabling process management including start, stop, check status, send input, and read output.

Enables running planned batches of shell commands in parallel locally or over SSH, with dependency ordering, timeouts, cancellation, and per-task result collection.

Agent-native SSH control plane with a local Web Terminal, human-in-the-loop secret input, keychain-backed profiles, and user-confirmed uploads for Codex, Claude Code, and MCP-compatible coding agents.

A secure gateway that lets AI agents interact with APIs and SSH servers via scoped tokens, with credential injection, human-in-the-loop for dangerous commands, and MCP integration for tool access.

A custom MCP server for orchestrating Windows/Linux/macOS workstations, providing filesystem, shell, SSH, and personal productivity tools with security features like allowlisting and human-in-the-loop approval for writes.

Enables agents to use secrets without exposing them, by injecting values into commands and redacting them from all outputs and transcripts.

A human-in-the-loop SSH bridge for AI agents that requires approval for every command before execution on configured servers.

Enables file operations and bash command execution on the local workspace, securely exposed to ChatGPT via OpenAI Tunnel.

A server that enables programmatic interaction with an already running Abaqus/CAE GUI application, allowing users to execute Python scripts and retrieve message logs through the Model Context Protocol (MCP).

Give Claude direct access to your AWS account, SSH into your servers, run shell commands on your laptop, query your databases, and manage PM2 processes — all from a Claude chat. No Claude Code subscription needed. Your keys never leave your machine.

Enables a trusted operator to drive a Windows workstation remotely over OAuth-protected Streamable HTTP, running PowerShell commands and file edits with checkpoints, durable jobs, and native service support.

A throwaway Docker sandbox for agents to run code and shell commands safely.

MCP server that turns coding workflows into explicit execution graphs (DAG) with deterministic command execution, human-in-the-loop gates, and tamper-proof run history for Claude Code.

A local MCP server that gives Claude in the browser tools to interact with a Fedora machine, including file operations, system diagnostics, build tasks, and root actions via Polkit.

Governed execution cells for AI agents via MCP; provides shell, code, file, and browser tools inside isolated, policy-enforced Citadels with deny-by-default security, human-in-the-loop approvals, and tamper-evident audit trails.

Lets an AI agent work on a real Commodore Amiga over the home network: AmigaDOS Shell, files, ARexx, screenshots, mouse and keyboard, and windows, gadgets and menus by name. Includes a remote desktop to watch and take over, tuned for 68000 machines and slow links.

Web-based SSH connection manager with an MCP server that enables AI agents to manage remote hosts via terminals, file transfers, and port forwarding, featuring human-in-the-loop approval for secure access.