# openFlow [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/molkex/mcp-flow-google  
**GitHub Stars:** 7  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/openflow

## Description
Omni Flash and Veo video, Nano Banana images on Google Flow, from any MCP client

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "openflow": {
    "url": "https://img.shields.io/badge/MCP-server-000?logo=modelcontextprotocol&logoColor=white)](https://modelcontextprotocol.io"
  }
}
```

## Documentation & README

# openFlow — MCP server for Google Flow: Veo video and Nano Banana images

**Generate video and images inside Claude Code, Cursor or any MCP client — through Google Flow,
on your own account.**

[![MCP](https://img.shields.io/badge/MCP-server-000?logo=modelcontextprotocol&logoColor=white)](https://modelcontextprotocol.io)
[![Works with Claude Code](https://img.shields.io/badge/works%20with-Claude%20Code-d97757)](https://claude.com/claude-code)
[![Works with Cursor](https://img.shields.io/badge/works%20with-Cursor-000)](https://cursor.com)
[![Live service](https://img.shields.io/badge/live-openflowmcp.com-2ea44f)](https://openflowmcp.com)
[![License](https://img.shields.io/badge/docs-MIT-blue)](LICENSE)

```bash
claude mcp add --transport http openflow https://openflowmcp.com/mcp
```

That is the install. No API key to buy, no SDK, no card. Ask your agent to *"generate a paper boat
on a puddle"* and you get a 1376×768 image in about eighteen seconds.

Video runs on **Veo**, images on **Nano Banana** — the same models Google Flow uses in the browser,
except your agent drives them. Google has no public API for either; this server is the missing wire.

<p align="center">
  <img src="https://openflowmcp.com/v1/showcase/4c37da6f-bbcc-4ad9-9774-f1a1e68b6976.jpg" width="32%" alt="A black hole distorting nearby light, generated through this MCP server">
  <img src="https://openflowmcp.com/v1/showcase/f0d3678c-4ef1-4eec-bce1-07323f04fcc6.jpg" width="32%" alt="Cinematic winter scene generated through Google Flow">
  <img src="https://openflowmcp.com/v1/showcase/a62f173d-2d2d-477d-8378-c9e39b360854.jpg" width="32%" alt="Supernova casting cosmic dust, generated by an AI agent">
</p>
<p align="center"><sub>Made by agents through this server ·
<a href="https://openflowmcp.com">300+ more in the live gallery</a></sub></p>

---

## Why you would want this

Google Flow makes some of the best images and video available today, and has **no public API**.
This server is the missing piece: MCP on the side your agent speaks, Flow on the other.

- **Images cost you nothing.** Google's image models are free on a normal account. Not "free tier
  with 50 credits" — free.
- **It runs on your account, not ours.** Your credits, your quota, your files. We are the wire, not
  the meter.
- **Your agent already knows how to use it.** 31 tools with descriptions written for a model to
  read, not for a docs page. No prompt engineering to make it pick the right one.
- **Failures tell you what to do.** Every refusal names the cause, the next step and whether waiting
  helps. Nothing ever answers just "error".

---

## Three steps

**1 · Connect the server**

```bash
claude mcp add --transport http openflow https://openflowmcp.com/mcp
```

For Cursor, Cline and everything else:

```json
{
  "mcpServers": {
    "openflow": {
      "type": "http",
      "url": "https://openflowmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}
```

**2 · Let the agent get a key**

Say *"check openflow status"*. With no key it registers one itself — no form, no waiting, no
approval queue.

**3 · Connect your Google account**

Say *"connect my Google account to openflow"*. A small script runs **on your machine**, opens
Google's own login page, and prints a one-time token. Your password is typed into Google's page, in
your browser, and never passes through this service.

Then just ask:

```
draw a red fox in the snow, vertical
make a 4-second video of that fox running
upscale it and save both into ./media
```

📖 [Full walkthrough for Claude Code →](https://github.com/molkex/mcp-flow-google/blob/HEAD/examples/claude-code.md)

---

## What your agent gets

| Group | Tools |
|---|---|
| **Images** | `generate_image`, `upscale_image`, `generate_scene` — the last one builds a location from a 3D layout map, so several shots share one geometry instead of drifting |
| **Video** | `generate_video`, `generate_video_from_image`, `generate_video_between_frames`, `generate_video_with_reference`, `extend_video`, `edit_video`, `upscale_video` |
| **Characters** | `create_character_from_photo`, `create_character_from_description`, `generate_with_face`, `generate_character_turnaround`, `generate_character_expression_sheet`, `list_characters`, `update_character` |
| **Music** | `music_generate` — a full track with lyrics and style control; `music_stems` splits it back into vocals and instruments |
| **Status** | `flow_status`, `flow_health`, `flow_dashboard`, `check_credits`, `check_job`, `list_models`, `fetch_media` |

Five ready-made **scenarios** come with it (MCP prompts): UGC video with a character, character
turnaround, expression sheet, generate-then-refine, one location from several camera angles.

**Things people ask an agent for, and get in one sentence:** *"generate a video in Claude Code"*,
*"make a Veo clip from this image"*, *"turn this photo into a character and shoot it from three
angles"*, *"upscale that video"*, *"write a track with these lyrics"*.

**Models.** Images: Nano Banana 2 (default, ~30 s), Nano Banana Pro (best), Nano Banana 2 Lite.
Video: 4/6/8/10-second clips, image-to-video, reference-to-video, interpolation between two frames,
extension of an existing clip. `list_models` returns the current verified list with credit prices —
the server never invents a model id.

---

## Keeping things consistent

Four behaviours worth knowing before you fight them. All measured against this server on
2026-08-23, not guessed.

**Build reference cards, don't describe the whole scene.** One call re-rolls everything at once:
fix the focus and the freckles change, fix the freckles and the bottle changes size. Instead
generate one approved frame per element — the person, the product, the room — and pass their
`media_id`s as `image_inputs`. Three references held together in a single 21-second call: same
face, same room, same object, only the arrangement changed.

**Render label text on its own.** Text inside a busy scene comes back mangled or mirrored. The
same words on a plain grey background, generated as a standalone product shot, come out clean —
and arrive correct when that shot is used as a reference. Note that a label stops being readable
once the object is small in frame, so brand names need their own close-up.

**For video, `i2v` holds detail and `r2v` holds identity.** `generate_video_with_reference` treats
your frame as an example and rebuilds the scene, so faces survive but small things drift — a hair
strand lying across a cheek was present at two seconds and gone by six. `generate_video_from_image`
continues that exact frame instead, and the same strand survived start, middle and end. Use r2v
when you have no frame yet, i2v when you do.

**`generate_scene` fixes geometry, not materials.** The layout map places objects at true positions
and depths reliably. Left alone it will still reinvent the architecture between shots — one camera
gave an ordinary window, another gave floor-to-ceiling glazing and a mountain view. Pass the room's
own reference frame in `image_inputs` alongside the layout and the materials hold.

---

## What it costs

| | |
|---|---|
| **Images** | **free.** A brand-new key gets 25 before linking a GitHub account; linking is one click, free, and removes the limit for good |
| **Video** | your own Google credits — 7 for 4 seconds, 10 for 6, 12 for 8 — plus a subscription here, which is what keeps the service running |
| **Subscription** | **$6 for a month**, $15 for three, $24 for six, $36 for a year — that last one works out to $3/month. It unlocks video and lets you keep your work out of the public gallery |
| **Everything else** | nothing. No per-image fee, no markup on credits, no seat pricing |

Pay by card, or send **USDT directly** — TRON (TRC20), BNB Smart Chain (BEP20), TON or Solana. The
crypto path takes no processor and no fee: you transfer to an address, the subscription turns on by
itself once the network confirms.

---

## Honest limits

Written down because finding them yourself costs an evening:

- **8 simultaneous generations per Google account.** Measured against Google's own ceiling, not
  guessed. Going over returns a wait, not an error — the job goes back in the queue and retries by
  itself.
- **Nano Banana Pro has its own daily quota** per account, separate from credits.
- **Files stay on the server until the disk runs low**, and even then only files you already
  downloaded get removed. Anything you never fetched is never deleted. Every result comes back with
  a direct download link — save it into your project and it is yours for good.
- **One Google account is one pool of credits.** Attach several and the work spreads across them,
  and your own rate limits rise with the count.

---

## Privacy

- Your Google password never reaches this service. The login happens in your browser, on your
  machine; only a token is passed on.
- Tokens are stored encrypted (AES-256-GCM), with the encryption key kept apart from the database.
- Your generations are visible only to your key. The public gallery shows only work whose owner
  chose to leave it public.
- The whole story, in plain words: [openflowmcp.com/trust](https://openflowmcp.com/trust)

---

## Questions people actually ask

**Do I need a paid Google Flow subscription?**
No. A normal Google account generates images for free. Video spends that account's credits, which
come with Google AI plans.

**Is my account at risk?**
The server uses the same tokens Google's own apps use, and nothing else. The concurrency cap exists
precisely so your account is never hammered.

**Can my Google account get disconnected?**
The link can drop — if you change your Google password, revoke sessions, or remove the device in
Google security settings. Nothing is lost when it happens: reconnecting takes a minute, and the
service tells you about it directly instead of leaving you to guess from a failed generation.

**How do I pay if cards do not work in my country?**
Send USDT on TRON, BSC, TON or Solana. The cabinet shows an address and an exact amount; the
subscription turns on by itself once the network confirms — usually within a minute.

**Can I attach several accounts?**
Yes, and you should — work spreads across them and your rate limits rise with the count.

**What if something breaks?**
Every refusal says what happened and what to do next. If one ever leaves you guessing, that is a
bug worth reporting: [t.me/mxmtkchk](https://t.me/mxmtkchk).

**Is the server open source?**
No. This repository is the documentation; the service is closed-source and hosted.

---

## Start

```bash
claude mcp add --transport http openflow https://openflowmcp.com/mcp
```

| | |
|---|---|
| 🌐 Service | **[openflowmcp.com](https://openflowmcp.com)** |
| 🔌 MCP endpoint | `https://openflowmcp.com/mcp` |
| 👤 Your cabinet | [openflowmcp.com/account](https://openflowmcp.com/account) |
| 🔒 What is stored | [openflowmcp.com/trust](https://openflowmcp.com/trust) |
| 📄 Terms | [openflowmcp.com/terms](https://openflowmcp.com/terms) |
| 💬 Support | [t.me/mxmtkchk](https://t.me/mxmtkchk) — one channel, and it answers |

<sub>Not affiliated with Google. "Google Flow" and "Veo" are trademarks of Google LLC.</sub>

