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.
An MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.
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.
Enables operating SSH terminals inside the Codex App plugin panel on Windows with a WSL backend, including local password autofill, private 2FA code entry, jump-host chaining, and long-lived connection recovery. Codex runs commands over an isolated channel so user terminal sessions and the main SSH connection stay under user control.
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.
Provides secure filesystem access for AI models through the Model Context Protocol with strict path validation, file operations, directory management, and system command execution within predefined directories.
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.
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 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.
A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.
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.
An MCP server that exposes a sandboxed task runner protocol to any MCP client, enabling evidence-protected task execution, exit protocol reading, and autopsy reports.
MCP server that integrates Claude with the Kyushu University supercomputer Genkai's TCS (PJM) job scheduler. It enables natural language control of job submission, status monitoring, deletion, resource queries, and reading output files.
Enables autonomous forensic investigation of disk images by mounting evidence, scanning for malware, and generating courtroom-ready reports using SIFT Workstation tools.
Conductor gives Claude persistent control of a local task runner, allowing automation of scripts, scheduling, pipelines, and email reports through natural language conversation.
Provides secure, disposable, resource-bounded container sandboxes that let AI agents create and inspect files, run shell commands with timeouts, and perform Git operations without exposing the host environment.
A secure MCP server for executing whitelisted shell commands with resource and timeout controls, designed for integration with Claude and other MCP-compatible LLMs.
Combines the sapper-v2 security assessment toolkit—fact-intent graphs, flag ledger, agent orchestration, and reporting—with LinuxMCP’s system and desktop control tools in a single MCP server. Enables users to run commands, record findings, orchestrate agents, and generate reports for authorized application debugging and security hardening from one MCP client.
A comprehensive all-in-one MCP server with 172 tools across 21 categories including Git operations, tmux monitoring, log aggregation, system resource monitoring, and GitHub integration. Features enterprise-grade security, intelligent caching, cross-platform support, and zero-configuration setup for Claude Desktop.
Enables AI agents to drive real terminal sessions — starting, typing, reading the screen, waiting on prompts and killing processes — while a human watches and can type into the same live session from a browser. Exposes twelve MCP tools for session control, snapshotting, finding text and sharing viewer links.
MCP server for infrastructure discovery and remote management, enabling SSH command execution, file transfer, log tailing, and machine/service inventory with a companion web dashboard.
Enables AI agents to see and control Android devices through ADB and screen mirroring, supporting screen capture, touch input, app management, UI element finding, file transfer, shell commands, clipboard access, and audio/video streaming.
A zero-config MCP server that provisions and fully administers Windows RDP boxes (Windows 10/11 and Server 2016–2025), exposing 144 tools for shell, files, registry, GUI automation, UAC elevation, health reports, and more, plus guided workflows.
Enables an MCP client to run and test shell commands inside a restricted, resource-limited Linux container with a persistent working directory across calls. It also exports files or directories from the sandbox as tar.gz archives returned as binary MCP resources.
Enables Windows program management through MCP, including listing installed programs, uninstalling software, force removal, and cleaning residual files. Supports generating detailed Markdown reports of system programs with smart categorization and statistics.
A server that exposes Pi-hole functionality as tools for AI assistants, allowing them to retrieve local DNS settings and query history through natural language.
Enables an MCP client to run commands and inspect or edit files across multiple named SSH hosts through a single local connection, keeping terminal state between calls and reading long output a page at a time. It reports honest exit statuses and handles router CLIs and pagers such as --More-- without dumping whole logs into the conversation.
A local TypeScript MCP gateway that unifies SSH, Prometheus, and MySQL tools under a single loopback HTTP service, featuring a web console for configuration and health monitoring.
Enables an AI agent to inspect and operate a remote Windows machine over a private tailnet, listing and reading files, transferring and mutating them within a configured sandbox root, capturing screenshots, and — only when explicitly double-opted-in — executing commands and sending keystrokes. It runs self-hosted with no third-party client or vendor cloud in the session path, and reports its live policy rather than asserting its own safety.
Enables AI agents to launch and manage system processes with strict security controls through executable allowlists, resource monitoring, and output capture capabilities.
A lightweight, zero-agent SSH operations tool that enables remote command execution, file transfer, and audit logging. It integrates as an MCP server for AI-driven infrastructure management.
MCP server that enables AI to see and control a physical computer via a JetKVM device for screen viewing, mouse/keyboard input, media mounting, and power management.
Exposes a Kali pentesting sandbox to OpenCode agents, enabling health checks, command execution, browser automation, file transfer, finding capture, and report finalization for authorized security scans without requiring LLM keys for the server.
Enables executing shell commands and rendering their ANSI-colored output as styled PNG terminal screenshots with selectable themes, window chrome, watermarks, and timestamps. Useful for pentest reports, documentation, and professional terminal captures.
A TypeScript prototype for an MCP-style registry providing local utility tools for shell command execution, filesystem access, and search functionality. It features Zod input validation and project manifest resource exposure for embedding into larger MCP implementations.
Enables SSH-based read-only monitoring of Linux vServers via Claude, allowing queries for system metrics, logs, network info, and health check reports.
Enables MCP clients to list SSH hosts, test reachability, retrieve Linux resource metrics, index and search project files, and run remote SSH commands when allowed, with local-first and safety-focused operations.
A Python-based template for creating modular command center servers using the Mondel Context Protocol that provides a structured foundation for building scalable applications with mathematical operations and modular arithmetic functions.
Connects MCP clients to a Kali Linux terminal for AI-assisted penetration testing and CTF challenge solving by executing commands like Nmap, Metasploit, and custom scripts.
Connects LLMs to a Kali Linux host over SSH for authorized penetration testing, exposing tools organized by pentest phases (recon, enumeration, exploitation) with scope guardrails.
Enables an agent to run shell commands through a JupyterLab/JupyterHub-hosted terminal, using REST API and WebSocket via Selenium for session handling, when SSH is not available.