veo-prompting 100/100 — SaferSkills

Is veo-prompting safe to install?

SaferSkills independently audited veo-prompting (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

README.md · 1 file

README.md9.7 KB · Markdown

<div align="center"> <img src="assets/banner.png" alt="Gemini Media MCP" width="100%">

<h1>Gemini Media MCP</h1> <p><strong>All-in-one MCP toolkit for AI media generation -- VEO 3.1 video + NanoBanana Pro 2 images + prompting skills</strong></p>

<p> <a href="#whats-included">What's Included</a> • <a href="#quick-start">Quick Start</a> • <a href="#veo-server">VEO Server</a> • <a href="#nanobanana-server">NanoBanana Server</a> • <a href="#prompting-skills">Skills</a> • <a href="#contributing">Contributing</a> </p> </div>

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 — or both. Each server publishes to PyPI separately.

Option A — `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 — 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 — 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/
├── servers/
│   ├── veo/                       # VEO 3.1 MCP Server (PyPI: veo-mcp-server)
│   │   ├── pyproject.toml
│   │   ├── requirements.txt
│   │   └── src/
│   │       └── veo_mcp_server/
│   │           ├── __init__.py
│   │           ├── __main__.py
│   │           └── server.py
│   └── nanobanana/                # NanoBanana MCP Server (PyPI: nanobanana-imagen-mcp)
│       ├── pyproject.toml
│       ├── requirements.txt
│       └── nanobanana_mcp_server/ # Package
├── skills/
│   ├── veo-prompting/             # VEO prompting skill
│   │   └── SKILL.md
│   └── nanobanana-prompting/      # NanoBanana prompting skill
│       └── SKILL.md
├── plugins/                       # Claude Code Plugin Marketplace
│   ├── veo-prompting/
│   │   ├── .claude-plugin/
│   │   │   └── plugin.json
│   │   └── skills/
│   │       └── veo-prompting/
│   │           └── SKILL.md
│   └── nanobanana-prompting/
│       ├── .claude-plugin/
│       │   └── plugin.json
│       └── skills/
│           └── nanobanana-prompting/
│               └── SKILL.md
├── .claude-plugin/
│   └── marketplace.json
├── .env.example
├── .gitignore
├── CHANGELOG.md
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── llms.txt
└── 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 ❤️ in the Eastern Province of Saudi Arabia.

veo-prompting— plugin

Is veo-prompting safe to install?

What is This?

What's Included

MCP Servers

Claude Code Skills (Plugin Marketplace)

Quick Start

Option A — `uvx` (zero-install, recommended)

Option B — clone + editable install

VEO Server

NanoBanana Server

VEO Server

Tools

VEO Configuration

VEO Models

NanoBanana Server

Tools

Models

Prompting Skills

VEO Prompting Skill

NanoBanana Prompting Skill

Architecture

Contributing

License

Credits

Support

Audit the pieces. Scan the whole. Decide.

Is veo-prompting safe to install?

What is This?

What's Included

MCP Servers

Claude Code Skills (Plugin Marketplace)

Quick Start

Option A — uvx (zero-install, recommended)

Option B — clone + editable install

VEO Server

NanoBanana Server

VEO Server

Tools

VEO Configuration

VEO Models

NanoBanana Server

Tools

Models

Prompting Skills

VEO Prompting Skill

NanoBanana Prompting Skill

Architecture

Contributing

License

Credits

Support

Audit the pieces. Scan the whole. Decide.

Option A — `uvx` (zero-install, recommended)