"Understanding Boss Mode" matching MCP servers:

An MCP server that implements Claude Code-like functionality, allowing the AI to analyze codebases, modify files, execute commands, and manage projects through direct file system interactions.

Mac file and terminal tools for local AI clients, plus an opt-in ChatGPT Developer Mode relay. Checked edits, bounded reads and real exit codes. Free MIT agent; OpenAI listing under review. Owner-level access, not a sandbox.

MCP-native infrastructure ops for deploying and managing self-hosted OpenClaw instances across cloud providers or local VMs, with read-only mode, destructive-action confirmation, and audit logs.

mcp-node-zig is an MCP server for remote machines. Drop it on a build box, a homelab server, a Windows host or a VPS, and any MCP client can run commands, drive long-running processes and read and write files there over one authenticated HTTP endpoint.

MCP server for E2B code sandbox, enabling creation, management, and execution of code in secure sandboxes using Python and shell commands.

Enables MCP clients to access a local computer through a controlled, permission-based tool surface for read-only or developer-mode file, process, and terminal operations.

Enables an MCP client to observe and control a text-mode DOS system via a Python bridge, supporting keyboard input and screen capture.

MCP server for Webmin system administration. 61 tools across 12 modules covering system monitoring, services, users, cron, packages, files, storage (SMART + LVM), security (Fail2ban), MySQL databases, Webmin ACL, and disk quotas. Four-tier safety framework with safe mode on by default. Python, MIT license, Docker and local deployment supported.

An MCP server that provides secure code execution capabilities using AWS Bedrock AgentCore's CodeInterpreter, supporting Python, JavaScript, TypeScript, shell commands, and file operations.

Persistent SSH sessions for AI assistants, enabling long-running remote shell connections with features like file transfer, port forwarding, and swarm mode.

MCP server wrapping Kimi Code CLI (kimi-k2.5) to provide tools for filesystem, shell, web, and agent operations.

An MCP server that enables AI agents to execute terminal commands and Python code on the host system, leveraging Agent Zero's battle-tested implementation with session management and smart output handling.

Enables LLM clients to execute shell commands safely through the MCP protocol, with features like session management, safe mode, and process control.

Open-source MCP server for managing Hetzner Cloud infrastructure with two management layers: * Layer 1 — Hetzner Cloud API (35 tools): Server power control, metrics, snapshots, backups, firewalls, DNS zones and records, rescue mode, server rebuild and rescale. Works even when the server OS is unresponsive. * Layer 2 — SSH (25 tools): Service management (systemd), Nginx config and reload,

Enables reading and editing local files, running shell commands, inspecting processes, and working with local projects through a local-first, self-hosted server, with optional experimental browser and desktop clients.

Enables Claude AI to run terminal commands, perform file operations, and manage git in a project directory via the Model Context Protocol.

Enables agent-style remote development over SSH with file operations and command execution, exposing native tools for searching, editing, and transferring files on remote machines.

Lets AI agents control a Keenetic router over the local network through the Model Context Protocol, managing devices, Wi-Fi, port forwarding, KeenDNS, DNS, DHCP, firewall, mesh, storage, logs and diagnostics with a safe, read-back-verified change model. An opt-in SSH mode additionally enables Entware package management and config file editing on the router.

MCP server for CachyOS connecting ChatGPT in developer mode to inspect and operate files, terminal, processes, apps, clipboard, and KDE/Wayland desktop.

A plugin for the Tabby terminal emulator that allows AI assistants to execute commands, manage SSH sessions, and read terminal buffers through the Model Context Protocol. It includes a pair programming mode with confirmation dialogs to ensure safe and controlled terminal automation.

Enables AI agents to safely execute Python code and shell commands in an ephemeral, isolated scratchpad with pre-execution AST security checks, timeout enforcement, token-shielded output, and file diff tracking. It also exposes static code-security inspection to flag forbidden imports and reflective escape attempts before execution.

Enables MCP clients like arena.ai Agent Mode or Claude Desktop to securely control real machines (VPS, Mac/Linux, Android) through a single URL and token, with a password gate protecting unauthorized directories.

A local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.

Enables ChatGPT Chat Mode to run commands on remote hosts and manage their files through secure connections, with profiles, host-key checks, and bounded responses.

Enables MCP clients to observe and control the Windows desktop through the UI Automation accessibility tree — no vision model required — by exposing tools for reading windows and interactive elements, clicking, typing, scrolling, shortcuts, PowerShell, screenshots, virtual desktops, web scraping, file operations and persistent memory, including background-window control without stealing focus. An optional agent mode adds a single natural-language task tool that runs the full upstream agent loop when an LLM provider is configured.

MCP server that enables AI clients to orchestrate multi-node LAN agents, with tools for remote command execution, file transfer, task delegation, and cross-node collaboration.

A minimal MCP server that executes commands on remote hosts by delegating to the local ssh binary, supporting batch-mode execution and optional timeout.

Enables ChatGPT Web conversations to operate a Windows computer through MCP with local tools, permissions, task state, and audit evidence.

Gives AI agents controlled access to a computer for browsing, editing, searching, and organizing files; creating and extracting zips; running terminal commands; managing background processes; and transferring files. Supports automatic public tunnel access plus options to restrict folders, use read-only mode, disable the terminal, and expire download/upload links.

Enables bidirectional communication with Claude via WhatsApp, allowing commands, file sharing, and persistent context without needing Claude Code open.

This MCP server lets Windows-based AI agents execute bash commands, read and write files, list directories, and translate paths between Windows and Linux formats across installed WSL distributions. It runs each operation through wsl.exe with real exit codes, supports a read-only mode, and can target a specific distro or fall back to the default one.

Enables Notion Custom Agents to execute terminal commands and manage files on a Windows host via MCP, with restricted mode for safety.

This server gives AI clients a persistent, isolated Linux container in which the model can run any bash command as root with internet access, install packages and start long-running processes without command filtering. Files produced inside it can be handed back to the user as signed, expiring public download links suitable for PDFs, images, audio and video.

Gives a Microsoft Copilot Studio agent Claude-Code-style tools to read, edit, search, and run shell commands against your local filesystem.

Wraps any CLI tool and exposes its subcommands as MCP tools with typed parameters, supporting both config-driven mode for structured commands and fallback mode for raw CLI execution.

Enables AI agents to manage remote servers via SSH, including command execution, multi-host batch operations, SFTP file transfer, background job handling, DevOps diagnostics, port tunneling, and safety guardrails like high-risk command blocking and read-only mode.

A secure, local-first MCP coding and computer-use harness for ChatGPT and Codex, enabling guarded file operations, durable terminals, Git review, local skills, and macOS computer control.

Enables AI agents to interact with terminal environments through multiple concurrent PTY sessions. Supports cross-platform terminal operations including command execution, session management, and real-time communication.

A Zsh execution tool for Claude Code providing yield-based command execution, PTY mode for interactive programs, circuit breaker for timeout protection, and adaptive learning (A.L.A.N.) for retry detection and proactive insights.

An extensible Message Communication Protocol server that provides secure code execution capabilities in isolated sandbox environments, compatible with Claude for Desktop and other MCP clients.