"OpenAI Gym" matching MCP servers:

Enables OpenAI Codex to delegate tasks to Google Antigravity CLI, running them headlessly and polling for results.

A controlled Model Context Protocol bridge that lets OpenAI Codex delegate work to Google Antigravity CLI on demand, with project-scoped opt-in and read-only delegation.

Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel.

A local MCP server that delegates tasks to a subagent runtime via OpenAI-compatible interfaces, enabling file operations, command execution, and rollback of local file changes.

Bridges the OpenAI Codex CLI app-server to MCP clients, letting agents launch and resume Codex coding sessions within a chosen workspace under configurable sandbox and approval policies. It exposes tools for sending prompts, long-polling task progress and live command output, approving or canceling runtime requests, and listing or reading past session history.

MCP server that turns ChatGPT Web or any MCP client into a coding agent on your own repositories, enabling file editing, command execution, testing, and git workflow without an OpenAI API key.

A CLI agent that controls Spotify through natural language commands, leveraging the Model Context Protocol to separate Spotify tools from the LLM client, and supporting multiple AI providers like Groq, Gemini, and OpenAI.

MCP server that gives AI coding agents (Claude Code, Cursor, Cline, etc.) access to multiple AI models through Antigravity CLI and OpenAI Codex CLI, enabling mid-conversation model consultation and code review.

A Model Context Protocol (MCP) server that lets you seamlessly use OpenAI's models right from Claude.

A local MCP runtime that lets MCP clients such as ChatGPT inspect workspaces, search, read, write, and patch files, manage directories, run shell commands, and control persistent processes on your machine through an outbound Device Relay connection that needs no open inbound port. It can also publish a local loopback OpenAI-compatible model runtime as a Frely personal Provider.

Enables ChatGPT on the web or mobile to run commands and edit files on a Windows PC through OpenAI Secure MCP Tunnel without opening inbound ports or exposing a public address.

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

A local Windows MCP server that lets a ChatGPT/OpenAI MCP client list, read, write, search, move, and delete files within allowed roots, run PowerShell/CLI commands, start and manage long-running processes, and inspect or commit/push Git repositories. It binds to loopback with policy-gated shell and Git mutations plus a local JSONL audit log.

Self-hosted server that lets ChatGPT, Grok, and stdio MCP clients read and write files, run PowerShell/CMD and interactive processes, and drive the Windows desktop through screenshots, window info, clicks, drags, and keyboard input. It connects via OpenAI Secure MCP Tunnels, an OAuth authorization-code + S256 PKCE HTTPS endpoint, or local stdio, exposing 38 tools under the user's own Windows account.

Lets web ChatGPT and other MCP clients explore, read, and edit files under allowed local project roots, run whitelisted commands such as git and npm, and hand off or resume coding tasks with the local Codex CLI, optionally over an OpenAI Secure MCP Tunnel.

A server tool for running Deep Learning models that offers Shell execution, Ngrok connectivity, and Docker container hosting with support for multiple AI frameworks including Anthropic, Gemini, and OpenAI.

Connects AI assistants to a development machine through a persistent Desktop Commander stdio process and the official OpenAI tunnel-client, exposing file, terminal, search, and document tools.

A secure local STDIO MCP server that lets OpenAI Codex automate Abaqus FEM workflows: create model scripts, submit jobs, monitor solver logs, and extract ODB results.

Enables ChatGPT private connections to a local Mac runtime, letting each project folder be accessed through official OpenAI Secure MCP Tunnels for file edits, shell commands, and Git workflows.

MCP server that interfaces with Gemini and OpenAI CLI tools to enable AI model interactions. It provides a bridge to external AI CLIs with predefined model configurations.

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.