NanoBanana Pro 2
4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding
Ask AI about NanoBanana Pro 2
Powered by Claude Β· Grounded in docs
I know everything about NanoBanana Pro 2. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Gemini Media MCP
All-in-one MCP toolkit for AI media generation -- VEO 3.1 video + NanoBanana Pro 2 images + prompting skills
What's Included β’ Quick Start β’ VEO Server β’ NanoBanana Server β’ Skills β’ Contributing
| CLI | Install check | Version check |
|---|---|---|
veo-mcp-server | veo-mcp-server --help | veo-mcp-server --version |
nanobanana-imagen-mcp | nanobanana-imagen-mcp --help | nanobanana-imagen-mcp --version |
What is This?
Gemini Media MCP is a comprehensive toolkit that brings Google's most powerful AI media generation models into any MCP-compatible AI assistant. Generate 4K videos with VEO 3.1, create stunning images with NanoBanana Pro 2, and craft professional prompts with built-in skills -- all from a single repository.
What's Included
MCP Servers
| Server | Description | Tools |
|---|---|---|
| VEO 3.1 | AI video generation (text-to-video, image-to-video, extend, interpolate) | 9 tools |
| NanoBanana | AI image generation with NanoBanana Pro 2 (Pro + Flash models) | 4 tools |
Claude Code Skills (Plugin Marketplace)
| Skill | Description |
|---|---|
| VEO Prompting | 7-layer prompt engineering for cinematic VEO 3.1 videos |
| NanoBanana Prompting | 7-layer prompt engineering for photorealistic NanoBanana Pro 2 images |
Install skills via Claude Code:
/plugin marketplace add u2n4/gemini-media-mcp
Quick Start
This repo hosts two independent MCP servers. Install whichever you need β or both. Each server publishes to PyPI separately.
Option A β uvx (zero-install, recommended)
Add a block to your MCP client config (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf) using the appropriate server block below (see VEO Server / NanoBanana Server sections).
Option B β clone + editable install
git clone https://github.com/u2n4/gemini-media-mcp.git
cd gemini-media-mcp
# Create a virtual environment (uv pip install requires one β or pass --system)
uv venv
source .venv/bin/activate # macOS / Linux
# .venv\Scripts\activate # Windows PowerShell
# Install one or both sub-packages
uv pip install -e servers/veo
uv pip install -e servers/nanobanana
VEO Server
uvx (zero-install):
{
"mcpServers": {
"veo": {
"command": "uvx",
"args": ["veo-mcp-server"],
"env": {
"GEMINI_API_KEY": "your_key",
"VIDEO_OUTPUT_DIR": "./videos"
}
}
}
}
Claude Code:
claude mcp add veo -s user -e GEMINI_API_KEY=your_key -- uvx veo-mcp-server
pip install:
pip install veo-mcp-server
NanoBanana Server
uvx (zero-install):
{
"mcpServers": {
"nanobanana": {
"command": "uvx",
"args": ["nanobanana-imagen-mcp"],
"env": {
"GEMINI_API_KEY": "your_key"
}
}
}
}
Claude Code:
claude mcp add nanobanana -s user -e GEMINI_API_KEY=your_key -- uvx nanobanana-imagen-mcp
pip install:
pip install nanobanana-imagen-mcp
VEO Server
AI video generation powered by Google VEO 3.1. Uses an async job pattern where generation starts in the background and returns a job ID for polling -- no timeouts.
Tools
| Tool | Description |
|---|---|
veo_generate_video | Generate video from text prompt. Supports 720p/1080p/4K, 16:9 or 9:16, 4/6/8 second duration, negative prompts, reference images, seed control, and batch generation (1-4 videos). |
veo_image_to_video | Animate a reference image with a motion prompt. |
veo_interpolate_video | Create smooth transition between two frames (first frame + last frame). |
veo_extend_video | Extend an existing VEO video by ~7 seconds. 720p only, max 148 seconds total. |
veo_check_job | Check async job status. Call every 15-20 seconds until completed or failed. |
veo_list_jobs | List all generation jobs and their current status. |
veo_api_status | Check API key status -- keys configured, active key, keys remaining. |
veo_pricing_info | Show pricing per second for standard and fast models at all resolutions. |
veo_show_output_stats | Display generation statistics -- video count, total size, file details, job statuses. |
VEO Configuration
| Variable | Description | Default |
|---|---|---|
GEMINI_API_KEY | Primary API key (required) | -- |
GEMINI_API_KEY_BACKUP | Backup key for auto-rotation | -- |
VIDEO_OUTPUT_DIR | Output directory for videos | ~/veo-videos |
VEO Models
| Tier | Model | Best For |
|---|---|---|
| Standard | veo-3.1-generate-preview | Higher quality output |
| Fast | veo-3.1-fast-generate-preview | Quicker generation |
NanoBanana Server
AI image generation powered by NanoBanana Pro 2. Supports Pro (maximum quality) and Flash (fast) models with default 4K resolution.
Tools
| Tool | Description |
|---|---|
generate_image | Generate images using NanoBanana Pro 2 (Pro or Flash). Supports aspect ratio, resolution (up to 4K), negative prompts, thinking level, grounding, and reference images. |
upload_file | Upload reference image for editing or conditioning. |
show_output_stats | Display generation statistics -- image count, total size, file details. |
maintenance | Server maintenance and cleanup -- clear caches, remove temporary files. |
Models
| Model | Engine | Best For |
|---|---|---|
| Pro | Gemini 3 Pro Image | Maximum quality, complex scenes |
| Flash | Gemini 3.1 Flash Image | Fast generation, simple scenes |
Prompting Skills
VEO Prompting Skill
7-layer prompt engineering system for VEO 3.1:
- Cinematography (camera, shot type, lens, angles)
- Subject (characters, objects, material cues)
- Action (force-based verbs, timestamp beats)
- Environment (time of day, weather, depth layers)
- Lighting & Mood (physical light sources, color temperature)
- Audio Design (dialogue, SFX, ambient, music)
- Technical Controls (negative prompts, style anchors, film stocks)
NanoBanana Prompting Skill
7-layer prompt engineering system for NanoBanana Pro 2:
- Style & Art Direction (visual DNA)
- Scene Description (environment, atmosphere)
- Main Subject (hero element with extreme specificity)
- Camera & Lens (real camera specs for realism)
- Lighting (natural, studio, color temperature)
- Texture, Material & Color (tactile detail)
- Negative Prompts (quality guards)
Architecture
gemini-media-mcp/
βββ servers/
β βββ veo/ # VEO 3.1 MCP Server (PyPI: veo-mcp-server)
β β βββ pyproject.toml
β β βββ requirements.txt
β β βββ src/
β β βββ veo_mcp_server/
β β βββ __init__.py
β β βββ __main__.py
β β βββ server.py
β βββ nanobanana/ # NanoBanana MCP Server (PyPI: nanobanana-imagen-mcp)
β βββ pyproject.toml
β βββ requirements.txt
β βββ nanobanana_mcp_server/ # Package
βββ skills/
β βββ veo-prompting/ # VEO prompting skill
β β βββ SKILL.md
β βββ nanobanana-prompting/ # NanoBanana prompting skill
β βββ SKILL.md
βββ plugins/ # Claude Code Plugin Marketplace
β βββ veo-prompting/
β β βββ .claude-plugin/
β β β βββ plugin.json
β β βββ skills/
β β βββ veo-prompting/
β β βββ SKILL.md
β βββ nanobanana-prompting/
β βββ .claude-plugin/
β β βββ plugin.json
β βββ skills/
β βββ nanobanana-prompting/
β βββ SKILL.md
βββ .claude-plugin/
β βββ marketplace.json
βββ .env.example
βββ .gitignore
βββ CHANGELOG.md
βββ CONTRIBUTING.md
βββ LICENSE
βββ README.md
βββ llms.txt
βββ llms-install.md
Contributing
See CONTRIBUTING.md.
License
MIT -- see LICENSE.
Credits
- NanoBanana MCP Server: inspired by the nano-banana naming convention used across the MCP community. This is an independent implementation.
- VEO 3.1 by Google DeepMind
Support
If you find this useful, please star this repository!
Made with β€οΈ in the Eastern Province of Saudi Arabia.
