OpenAI MCP Server

Example Use Cases

• 1

  Generate or edit images programmatically using OpenAI-compatible image models (DALL·E 3, gpt-image-1, or Stable Diffusion variants).

• 2

  Convert text to speech or transcribe audio (TTS/STT) and store the resulting audio files locally.

• 3

  Submit and monitor long-running video generation tasks (text-to-video or image-to-video) with asynchronous notifications and optional ImgBed uploads.

Description

This MCP server centralizes multimodal generation workflows — image creation and editing, speech synthesis and transcription, and text/image-to-video via SiliconFlow — using OpenAI-compatible APIs. Time-consuming tasks (e.g., DALL·E 3 or gpt-image-1 image tasks and video generation) are handled asynchronously with result notifications sent via OneBot or Telegram. Generated media are stored locally and optionally uploaded to a configured ImgBed service; behavior and models are configurable via environment variables.