Что умеет

List Models: List Dora generation models, cheapest-first, with per-call coin cost. Call this when the user asks what models are available, when cost matters, or when you want to verify a model name. D

Generate Video: Generate a video. Default model: seedance_1_5_pro at 480p, 8s, no audio (cheapest reasonable quality). Before calling, if the user has not specified them, briefly ASK for: (1) aspect r

Generate Image: Generate an image. Default model: nano_banana_2 (good quality, ~100 coins, supports reference photo). Use z_image (10 coins) only if the user wants the cheapest possible result. Use na

Dora — AI Image & Video Generator

One OAuth-secured connector that exposes 14 leading AI image and video models to Claude.

Models Image — z_image, google_nano_banana, google_nano_banana_edit, gpt4o_image, gpt_image_2, nano_banana_2( default), nano_banana_pro

Video — grok_text_to_video, grok_image_to_video, seedance_1_5_pro (default, 480p / 8s), kling_2_6, veo_3, seedance_2_fast, seedance_2

Tools

Tool	What it does
`list_models`	Returns all models cheap-first with per-call cost
`generate_image`	Starts an image job (defaults to nano_banana_2 at 1K)
`generate_video`	Starts a video job (defaults to seedance_1_5_pro at 480p, no audio)
`check_job`	Polls a job; returns inline image content for small assets plus a full-size Firebase URL

Authentication

OAuth 2.1 with PKCE and Dynamic Client Registration (RFC 7591). No pre-shared keys — the MCP client handles the flow.

Pricing Pay-per-call in coins. Free tier ships with a starter balance; subscriptions add monthly coin packs. Full schedule at https://doravideo.com/pricing.

Links

App Store (iOS): https://apps.apple.com/app/id6747720520
Web: https://doravideo.com
Connector docs: https://github.com/Saga-Labs/dora-mcp
Contact: sagalabs@proton.me

Dora

Что умеет

Какие данные видит

Нужен ли аккаунт

list_models	List Dora generation models, cheapest-first, with per-call coin cost. Call this when the user asks what models are available, when cost matters, or when you want to verify a model name. Defaults: nano_banana_2 for images, seedance_1_5_pro for videos — only step up if the user explicitly asks for higher quality, face preservation, or audio.
generate_video	Generate a video. Default model: seedance_1_5_pro at 480p, 8s, no audio (cheapest reasonable quality). Before calling, if the user has not specified them, briefly ASK for: (1) aspect ratio (9:16 vertical, 16:9 horizontal, 1:1 square), (2) duration (4/8/12s), (3) whether they want audio, (4) resolution (480p/720p/1080p) — higher costs more. Skip the questions only when the user already gave you those details or asked for "the cheapest". Returns job_id; poll check_job until status=done.
generate_image	Generate an image. Default model: nano_banana_2 (good quality, ~100 coins, supports reference photo). Use z_image (10 coins) only if the user wants the cheapest possible result. Use nano_banana_pro (180-240) only when the user explicitly asks for face preservation or maximum quality. Default resolution 1K — never use 2K/4K unless the user explicitly asks. If aspect ratio matters and the user did not say, ASK whether they want 9:16 (vertical), 16:9 (horizontal), or 1:1 (square). Returns job_id; poll check_job until status=done.
check_job	Check the status of a generation job. Returns status (pending\|done\|failed) and result_url when done. Wait at least 30 seconds between polls — generations take 1-5 minutes typically.