# Molkex Omni Flash Veo3 Nano Banana MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.molkex%2Fomni-flash-veo3-nano-banana
Registry id: `mcp-registry/io.github.molkex/omni-flash-veo3-nano-banana`
Status: live (checked 2026-10-27T00:08:36.883Z)

## Measurements (30 days)

- Uptime: 99.87%
- Checks: 4987
- Outages (90 days): 4

## Install

```json
{
  "mcpServers": {
    "molkex-omni-flash-veo3-nano-banana-mcp-s": {
      "type": "http",
      "url": "https://openflowmcp.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http molkex-omni-flash-veo3-nano-banana-mcp-s https://openflowmcp.com/mcp
```

## Tools (51)

- `add_account_token`: Attach one of YOUR OWN Google accounts to the pool using an oauth_token captured on the USER'S OWN machine (password/2FA never leave it). This is the self-serve
- `add_antigravity_start`: Begin connecting a Google ANTIGRAVITY account (used by the Claude/Gemini models via OmniRoute — not a Google Flow account). Returns `authorize_url` and `state`.
- `add_antigravity_submit`: Finish connecting a Google Antigravity account started with add_antigravity_start. `code` is the value of `?code=...` on the antigravity.google/oauth-callback p
- `chat_claude_sonnet`: Запрос к Claude Sonnet 4.6 через вашу подписку Anthropic (если подключена) или через подписку Google (Vertex). Поддерживает инструменты (tool_use). Args: messag
- `chat_gemini_flash`: Быстрый и дешёвый Gemini 3 Flash — для коротких запросов, классификации, извлечения полей из текста. Идёт в вашу подписку Google, наши токены не тратит. Args: m
- `chat_gemini_pro`: Запрос к Gemini 3 Pro через вашу подписку Google AI Pro. Использует ваш подключённый Google-аккаунт (подключите на /connect-google). Расходует вашу квоту Google
- `check_credits`: Check projects for a Google account (or all). NOTE: for the credit BALANCE and a full at-a-glance overview, prefer `flow_dashboard()` — it returns real credit n
- `check_job`: Check the status/result of a job previously returned by generate_image, generate_video, generate_video_from_image, or generate_video_with_reference. Besides sta
- `complete_antigravity_account`: Finish an Antigravity account started with add_antigravity_submit. Creates the GCP project needed before the account can serve LLM requests. Idempotent — safe t
- `contact_support`: Send a message to the openFlow human operator (no Telegram needed). Replies come from a human, usually within hours; read them with support_replies.
- `create_character`: Create a new, empty Flow character (just gets you an entity_id — no portrait/body, no description yet). Plain HTTP, no browser involved. Low-level building bloc
- `create_character_from_description`: Invent a new character from a text description and generate its portrait — the full "make me a character, no photo involved" path in ONE call, instead of gluing
- `create_character_from_photo`: Create a new Flow character whose portrait (and optionally body) is a REAL PHOTO, not a text description or generation. Both photos become the character's slot-
- `create_project`: Create a NEW Flow project on one of your Google accounts and return its project_id. Use this to give every one of YOUR OWN clients their own namespace: create a
- `edit_video`: Rewrite a video from a plain description: "make the sky stormy", "take the passer-by out of the shot", "warmer light", "put the product from the image on the ta
- `extend_video`: Continue a video this service already generated — Flow writes what happens next. media_id: the id from a previous generate_video* result (the bare id, not the /
- `fetch_media`: Download a generated media file (video, frame) and return its bytes, base64-encoded, so the file can be saved or shown even though the media endpoint isn't publ
- `flow_dashboard`: The account-pool control panel: for EVERY Google account, the real credit balance, subscription tier, project count, and health status, plus totals — one call, 
- `flow_health`: Check whether the Flow generation backend is reachable and see current queue depth (queued + warming + running jobs), plus disk state (`disk`: free_gb, below_ta
- `flow_status`: What this key still needs before it can do everything — READ-ONLY, spends nothing. Call this BEFORE the first generation of a session, whenever a call is refuse
- `generate_character_expression_sheet`: Generate a single image showing the character's FACE with several different expressions in one row, labeled — an "expression sheet". Same job type and same hist
- `generate_character_image`: Generate a portrait or body image for an existing Flow character. entity_id: the character's entityId — from create_character or create_character_from_photo, or
- `generate_character_turnaround`: Generate a single image showing the character's FULL BODY from 3 angles (front/side/back) in one row, labeled — a "turnaround sheet". Pure HTTP as of 2026-07-26
- `generate_image`: Generate an image from a text prompt via Google Flow. model — pass ONE of these exact ids (from GET v1/flow/models, verified 2026-07-25): BELUGA = "Nano Banana 
- `generate_scene`: Build a location precisely from a scene-layout/v2 map and generate its plate. This is the "exact location building" path: instead of describing the room in pros
- `generate_video`: Generate a video from a text prompt via Google Flow (Veo models). video_model_key options: abra_t2v_4s (default, 7 credits), veo_3_1_t2v_lite (10cr, visibly cle
- `generate_video_between_frames`: Generate the transition between TWO given frames: the video starts at the first image and ends at the second one, Flow invents everything in between. This is Fl
- `generate_video_from_image`: Generate a video that starts from a given image (i2v — image-to-video). Pass exactly one start: start_image_base64 (raw base64 image bytes, no data: URI prefix)
- `generate_video_with_reference`: Generate a video using up to 7 reference images (r2v — e.g. a consistent character/subject across the video). reference_images_base64: raw base64-encoded image 
- `generate_voice`: Speak `text` aloud with a Gemini TTS voice and return a WAV (24 kHz, mono, 16-bit). Takes ~15-25 seconds. Costs no image/video quota. Russian, English and most 
- `generate_with_face`: Generate a NEW image of the SAME PERSON/character as an existing photo or portrait — dress them differently, move them somewhere else, make an avatar. This is t
- `list_available_llm`: Какие LLM-модели доступны этому ключу прямо сейчас, и какая у ключа квота. Делает два параллельных запроса: GET /llm/models (OmniRoute — список моделей и подклю
- `list_characters`: List the characters YOU created (create_character_from_description, or create_character_from_photo with name=...) and can now generate more images of via genera
- `list_live_models`: Live from Google, no credits, use to answer «is this model still working?». Reads Google Flow's own current model catalog (modelConfig: usage keys, per-tier cre
- `list_llm_accounts`: List the Google accounts you connected for the LLM relay with their tier (Free/Pro/Ultra); refresh=True re-checks the tier with Google. The model is chosen per 
- `list_models`: List every valid model id this service accepts — READ-ONLY, spends no credits, calls nothing outside this service. Call this BEFORE generate_image/generate_vide
- `list_voices`: The 30 Gemini TTS voices usable with generate_voice: name, gender, short description. Gender/description are a rough guide only; any voice reads any language.
- `music_chat`: Talk to the Google Flow Music Producer agent instead of one-shotting a track. Use this when the work is a conversation rather than a single brief: asking what i
- `music_credits`: Check remaining flowmusic credits and subscription tier.
- `music_download`: Download the raw .m4a file of a track to the server.
- `music_generate`: Generate a full song from a text brief via Google Flow Music (Lyria). prompt — free text: genre, mood, BPM, instruments, and whether you want vocals or an instr
- `music_get`: Get metadata for a single music track.
- `music_list`: List the user's music tracks.
- `music_stems`: Split a track we generated into stems (vocals, instrumental, drums, bass, …). clip_id — the id of a clip returned by music_generate (or music_video's song). Run
- `recast_video`: Re-make a video with YOUR character in place of the person in it: same camera, movement, gestures, timing and mouth movement, the character's look. character: n
- `refresh_llm_models`: Получить актуальный список LLM-моделей из каталога OmniRoute. OmniRoute сам опрашивает Google раз в час; `force_live=True` просит релей сходить в Google прямо с
- `set_character_voice`: Attach a preset Gemini TTS voice to a Flow character for auto-lipsync in future videos. Synthesizes a short reference audio in the chosen voice and attaches its
- `support_replies`: Your support thread, including operator replies (from a human, usually within hours). `since` is a unix timestamp: only newer messages.
- `update_character`: Save a character's display name and/or personality notes. Without this, a character stays 'Untitled Character' with no description even after portrait/body imag
- `upscale_image`: Upscale an existing generated image (from a prior generate_image call) to a higher resolution -- the same "1K/2K/4K" choice Flow offers when downloading. accoun
- `upscale_video`: Upscale an existing generated video (from a prior generate_video call) to a higher resolution -- the same "270p/720p/1080p/4K" choice Flow offers when downloadi

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.