# BananaBanana Image, Video & Speech Generation

Wires image, video and speech generation into your AI client. You pay per call from an account balance.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: bananabanana-pro-mcp
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/bananabanana-pro-mcp/bananabanana-mcp
- Updated: 2026-10-07
- HTML: https://affpapa.org/en/nevibecode/mcp/bananabanana-image-video-speech-generation

## What it does

The server hands your agent ten tools: a model list with prices, balance and top-up, plus generation and editing for pictures, clips and voice. Models span Google Nano Banana and Veo 3.1, Gemini Omni, OpenAI GPT Image 2.5, Alibaba Qwen Image and Wan 3.0, xAI Grok Imagine Video and Gemini TTS. Images go up to 4K, with one to four variants and up to 14 reference images.

Connection runs over streamable HTTP at `https://bananabanana.pro/api/mcp`. OAuth 2.1 is the main route: in Claude run `claude mcp add --transport http bananabanana https://bananabanana.pro/api/mcp`, then open `/mcp` in the session and pick “Authenticate”. Nothing to copy. Cursor, VS Code, Windsurf, Codex and scripts use a `bb_live_…` key in the `Authorization` header instead.

Spending comes out of a balance you fund with crypto or a card. Before an expensive call the server quotes the cost, and a failed job is refunded. Without a key or a finished OAuth flow the generation tools stay dead — you have to authorise first.

## Requirements
- Remote server: `https://bananabanana.pro/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http image-video https://bananabanana.pro/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add bananabanana-image-video-speech-generation --url https://bananabanana.pro/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "bananabanana-image-video-speech-generation": {
            "url": "https://bananabanana.pro/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "bananabanana-image-video-speech-generation": {
            "type": "http",
            "url": "https://bananabanana.pro/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http bananabanana-image-video-speech-generation https://bananabanana.pro/api/mcp
```

## When to use it
- generate a picture from a text prompt inside the agent chat
- edit a finished image with a written instruction
- build a clip from a first and last frame
- restyle or extend an existing video
- turn text into speech with Gemini TTS

## Example prompts
- List the models and their prices with `list_models`
- Generate a 16:9 image in 2K of a sunset over the sea
- Make a 5-second video from `first.png`

## Similar
- [bailian-gen](https://affpapa.org/en/nevibecode/skills/bailian-gen.md) — skill · 9200 installs
- [ai-video-generation](https://affpapa.org/en/nevibecode/skills/ai-video-generation.md) — skill · 872100 installs
- [image-to-video](https://affpapa.org/en/nevibecode/skills/101-skills-image-to-video.md) — skill · 55400 installs
- [qianwen-video-generation](https://affpapa.org/en/nevibecode/skills/qianwen-video-generation.md) — skill · 5500 installs
- [video-generation](https://affpapa.org/en/nevibecode/skills/video-generation.md) — skill · 3000 installs
- [eachlabs-video-generation](https://affpapa.org/en/nevibecode/skills/eachlabs-video-generation.md) — skill · 491 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md