"Building OpenAI Agents SDK Using Official Documentation" matching MCP servers:

A unified MCP-compatible system for controlling fleets of remote machines through AI agents.

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

A Python implementation of the Model Context Protocol that allows applications to provide standardized context for LLMs, enabling creation of servers that expose data and functionality to LLM applications through resources, tools, and prompts.

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

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

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

A minimal MCP server for UW Hyak (klone) that exposes tools to run shell commands and write files remotely, along with documentation resources for klone-specific utilities.

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

Exposes the official lark-cli as an MCP server, enabling agents to execute arbitrary CLI commands, query API schemas, and manage authentication.

Enables AI agents to deploy applications and manage servers over SSH using natural language commands, with built-in tools for Python bots, Docker Compose, and SSL setup.

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.

Production-ready, zero-knowledge AI DevOps deployment, infrastructure provisioning, self-healing execution, and persistent documentation engine for VPS servers.

Sandboxed bash execution MCP server for AI agents, using an in-memory virtual filesystem overlay to prevent real filesystem damage, with configurable network access, timeouts, and optional Python/JS runtimes.

An MCP server that enables AI assistants to control iTerm2 sessions, windows, tabs, and profiles using the official iTerm2 Python API. It includes a security model with session tagging and tiered permissions to ensure safe and controlled terminal interactions.

Enables AI assistants to natively execute and manage 600+ Kali Linux security, penetration testing, and forensic tools, including search, help documentation, structured scanners, and workspace management.

Provides data science, plotting, statistics, system, and web tools via MCP, with interactive CLI clients for OpenAI-compatible and Anthropic providers.

An MCP server that enables users to execute arbitrary shell commands on their local machine and receive the output. It provides a terminal tool for running system commands through MCP-compatible clients using the Python SDK.

Provides Unix command documentation directly within Claude conversations, allowing users to retrieve help pages, man pages, and usage information without leaving the chat interface.

Enables ChatGPT to control a Windows PC remotely via OpenAI Secure MCP Tunnel, executing file operations, PowerShell commands, and system actions through a local MCP server.

reference MCP server over STDIO — every SDK feature demonstrated