openai/mcp-extensions

Build plugins that feel like native, first-class features of ChatGPT.

What it solves

OpenAI MCP Extensions allows developers to create plugins for ChatGPT that go beyond basic text interaction, enabling them to behave like native, integrated features within the ChatGPT interface.

How it works

It extends the Model Context Protocol (MCP) by providing specific entry points and UI components. Developers use the provided TypeScript or Python SDKs to define how their plugin interacts with the ChatGPT sidebar, file viewers, the message composer, and custom input forms.

Who it’s for

This is for developers building plugins for ChatGPT who want to create a more seamless, interactive experience for users by adding custom UI elements and specialized workflows directly into the chat environment.

Highlights

  • Sidebar entrypoints for direct app access.
  • Custom file extension handlers for specialized file viewing.
  • Composer mentions to search and reference plugin resources directly in messages.
  • Extended forms for rich user input, such as thumbnail-based selection.

Related

  • Project
    yurineko73/Godot-MCP-Native

    A Godot Engine plugin that implements the Model Context Protocol (MCP), enabling AI assistants to read and modify scenes, scripts, and resources directly via natural language.

  • Project
    miuuyy/codex-chatgpt-web

    A bridge that integrates ChatGPT Web models into the Codex workflow, allowing users to use their ChatGPT account plans and tools via browser automation and MCP.

  • Project
    Waishnav/devspace

    DevSpace is a self-hosted MCP server that securely connects ChatGPT to your local machine, letting it read, edit, search, and run code in your own projects. You run it locally, expose it through a tunnel you control, and approve connections with a password. It supports Linux, macOS, and Windows (with Bash-compatible shells), requires Node >=22.19 <27, and is installed via npm.

  • Project
    openclaw/mcporter

    MCPorter is a TypeScript library and CLI that lets developers discover, call, and work with Model Context Protocol (MCP) servers. It provides commands for listing tools, invoking them, handling OAuth, generating typed clients or dedicated CLIs, and recording sessions. It also offers a runtime API (`createRuntime`, `callOnce`, `createServerProxy`) for programmatic use, supports multiple transport types (HTTP, stdio, SSE), and integrates with IDEs and Chrome DevTools via an OpenClaw relay.

  • Project
    kardolus/chatgpt-cli

    ChatGPT CLI is a cross‑platform command‑line client for many LLM providers. It offers streaming queries, thread‑based chat history, prompt‑file injection, multimedia I/O, and an experimental agent mode (ReAct / Plan‑Execute) that can run shell/file/web‑search tools under budget and policy constraints. It also supports the Model Context Protocol (MCP) for custom tool calls. Install via Homebrew or a pre‑built binary, configure API keys in `~/.chatgpt-cli/config.yaml`, and start chatting with `chatgpt "your question"` or `chatgpt --interactive`.