Generate an image via a logged-in web provider (ChatGPT web or Gemini web) and save it locally. Waits inline up to wait_seconds; if generation is still running, returns a job_id to poll with get_generation_status. The MCP does NOT judge quality — after completion, you (the caller) should view the saved file and decide whether to keep it or regenerate with a better prompt.

Edit an existing local image via a logged-in web provider: uploads the image, sends the edit instructions, and saves the edited result locally. Same job semantics as generate_image.

Generate the same concept with BOTH providers (ChatGPT web + Gemini web) in parallel and save both images locally, so you can visually compare them and pick the winner. Each provider can succeed or fail independently.

Check a generation/edit job started by generate_image, edit_image or generate_with_both. Returns status, saved file paths when finished, error details on failure, and recent job logs.

Copy a completed job's image(s) to an additional location. Note: jobs already save their output to the originally requested path automatically — use this only to place an extra copy somewhere else.

Check whether the persistent browser session for a provider is authenticated and usable. Never enters credentials — if not authenticated, it tells you to run provider_login so the user can log in manually.

Open the provider's website in the (headed) persistent browser and WAIT for the user to log in manually — including any CAPTCHA or MFA, which are never automated. Ask the user to complete the login in the opened window; returns once login is detected or the wait times out. Requires the server to run with PIXEL_BRIDGE_HEADLESS unset/false.