{ "markdown": "\n
\n \"Gemini\n\n

Gemini Media MCP

\n

All-in-one MCP toolkit for AI media generation -- VEO 3.1 video + NanoBanana Pro 2 images + prompting skills

\n\n

\n \"PyPI\n \"PyPI\n \"MCP\"\n \"MIT\"\n \"Claude\n \"Gemini\"\n

\n\n

\n What's Included •\n Quick Start •\n VEO Server •\n NanoBanana Server •\n Skills •\n Contributing\n

\n
\n\n---\n\n| CLI | Install check | Version check |\n|-----|---------------|---------------|\n| `veo-mcp-server` | `veo-mcp-server --help` | `veo-mcp-server --version` |\n| `nanobanana-imagen-mcp` | `nanobanana-imagen-mcp --help` | `nanobanana-imagen-mcp --version` |\n\n---\n\n## What is This?\n\nGemini 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.\n\n## What's Included\n\n### MCP Servers\n\n| Server | Description | Tools |\n|--------|-------------|-------|\n| **VEO 3.1** | AI video generation (text-to-video, image-to-video, extend, interpolate) | 9 tools |\n| **NanoBanana** | AI image generation with NanoBanana Pro 2 (Pro + Flash models) | 4 tools |\n\n### Claude Code Skills (Plugin Marketplace)\n\n| Skill | Description |\n|-------|-------------|\n| **VEO Prompting** | 7-layer prompt engineering for cinematic VEO 3.1 videos |\n| **NanoBanana Prompting** | 7-layer prompt engineering for photorealistic NanoBanana Pro 2 images |\n\nInstall skills via Claude Code:\n```\n/plugin marketplace add u2n4/gemini-media-mcp\n```\n\n## Quick Start\n\nThis repo hosts **two independent MCP servers**. Install whichever you need — or both. Each server publishes to PyPI separately.\n\n### Option A — `uvx` (zero-install, recommended)\n\nAdd 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).\n\n### Option B — clone + editable install\n\n```bash\ngit clone https://github.com/u2n4/gemini-media-mcp.git\ncd gemini-media-mcp\n\n# Create a virtual environment (uv pip install requires one — or pass --system)\nuv venv\nsource .venv/bin/activate # macOS / Linux\n# .venv\\Scripts\\activate # Windows PowerShell\n\n# Install one or both sub-packages\nuv pip install -e servers/veo\nuv pip install -e servers/nanobanana\n```\n\n### VEO Server\n\n**uvx (zero-install):**\n```json\n{\n \"mcpServers\": {\n \"veo\": {\n \"command\": \"uvx\",\n \"args\": [\"veo-mcp-server\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your_key\",\n \"VIDEO_OUTPUT_DIR\": \"./videos\"\n }\n }\n }\n}\n```\n\n**Claude Code:**\n```bash\nclaude mcp add veo -s user -e GEMINI_API_KEY=your_key -- uvx veo-mcp-server\n```\n\n**pip install:**\n```bash\npip install veo-mcp-server\n```\n\n### NanoBanana Server\n\n**uvx (zero-install):**\n```json\n{\n \"mcpServers\": {\n \"nanobanana\": {\n \"command\": \"uvx\",\n \"args\": [\"nanobanana-imagen-mcp\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your_key\"\n }\n }\n }\n}\n```\n\n**Claude Code:**\n```bash\nclaude mcp add nanobanana -s user -e GEMINI_API_KEY=your_key -- uvx nanobanana-imagen-mcp\n```\n\n**pip install:**\n```bash\npip install nanobanana-imagen-mcp\n```\n\n## VEO Server\n\nAI 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.\n\n### Tools\n\n| Tool | Description |\n|------|-------------|\n| `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). |\n| `veo_image_to_video` | Animate a reference image with a motion prompt. |\n| `veo_interpolate_video` | Create smooth transition between two frames (first frame + last frame). |\n| `veo_extend_video` | Extend an existing VEO video by ~7 seconds. 720p only, max 148 seconds total. |\n| `veo_check_job` | Check async job status. Call every 15-20 seconds until completed or failed. |\n| `veo_list_jobs` | List all generation jobs and their current status. |\n| `veo_api_status` | Check API key status -- keys configured, active key, keys remaining. |\n| `veo_pricing_info` | Show pricing per second for standard and fast models at all resolutions. |\n| `veo_show_output_stats` | Display generation statistics -- video count, total size, file details, job statuses. |\n\n### VEO Configuration\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `GEMINI_API_KEY` | Primary API key (required) | -- |\n| `GEMINI_API_KEY_BACKUP` | Backup key for auto-rotation | -- |\n| `VIDEO_OUTPUT_DIR` | Output directory for videos | `~/veo-videos` |\n\n### VEO Models\n\n| Tier | Model | Best For |\n|------|-------|----------|\n| Standard | `veo-3.1-generate-preview` | Higher quality output |\n| Fast | `veo-3.1-fast-generate-preview` | Quicker generation |\n\n## NanoBanana Server\n\nAI image generation powered by NanoBanana Pro 2. Supports Pro (maximum quality) and Flash (fast) models with default 4K resolution.\n\n### Tools\n\n| Tool | Description |\n|------|-------------|\n| `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. |\n| `upload_file` | Upload reference image for editing or conditioning. |\n| `show_output_stats` | Display generation statistics -- image count, total size, file details. |\n| `maintenance` | Server maintenance and cleanup -- clear caches, remove temporary files. |\n\n### Models\n\n| Model | Engine | Best For |\n|-------|--------|----------|\n| Pro | Gemini 3 Pro Image | Maximum quality, complex scenes |\n| Flash | Gemini 3.1 Flash Image | Fast generation, simple scenes |\n\n## Prompting Skills\n\n### VEO Prompting Skill\n7-layer prompt engineering system for VEO 3.1:\n1. Cinematography (camera, shot type, lens, angles)\n2. Subject (characters, objects, material cues)\n3. Action (force-based verbs, timestamp beats)\n4. Environment (time of day, weather, depth layers)\n5. Lighting & Mood (physical light sources, color temperature)\n6. Audio Design (dialogue, SFX, ambient, music)\n7. Technical Controls (negative prompts, style anchors, film stocks)\n\n### NanoBanana Prompting Skill\n7-layer prompt engineering system for NanoBanana Pro 2:\n1. Style & Art Direction (visual DNA)\n2. Scene Description (environment, atmosphere)\n3. Main Subject (hero element with extreme specificity)\n4. Camera & Lens (real camera specs for realism)\n5. Lighting (natural, studio, color temperature)\n6. Texture, Material & Color (tactile detail)\n7. Negative Prompts (quality guards)\n\n## Architecture\n\n```\ngemini-media-mcp/\n├── servers/\n│ ├── veo/ # VEO 3.1 MCP Server (PyPI: veo-mcp-server)\n│ │ ├── pyproject.toml\n│ │ ├── requirements.txt\n│ │ └── src/\n│ │ └── veo_mcp_server/\n│ │ ├── __init__.py\n│ │ ├── __main__.py\n│ │ └── server.py\n│ └── nanobanana/ # NanoBanana MCP Server (PyPI: nanobanana-imagen-mcp)\n│ ├── pyproject.toml\n│ ├── requirements.txt\n│ └── nanobanana_mcp_server/ # Package\n├── skills/\n│ ├── veo-prompting/ # VEO prompting skill\n│ │ └── SKILL.md\n│ └── nanobanana-prompting/ # NanoBanana prompting skill\n│ └── SKILL.md\n├── plugins/ # Claude Code Plugin Marketplace\n│ ├── veo-prompting/\n│ │ ├── .claude-plugin/\n│ │ │ └── plugin.json\n│ │ └── skills/\n│ │ └── veo-prompting/\n│ │ └── SKILL.md\n│ └── nanobanana-prompting/\n│ ├── .claude-plugin/\n│ │ └── plugin.json\n│ └── skills/\n│ └── nanobanana-prompting/\n│ └── SKILL.md\n├── .claude-plugin/\n│ └── marketplace.json\n├── .env.example\n├── .gitignore\n├── CHANGELOG.md\n├── CONTRIBUTING.md\n├── LICENSE\n├── README.md\n├── llms.txt\n└── llms-install.md\n```\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## License\n\nMIT -- see [LICENSE](LICENSE).\n\n## Credits\n\n- NanoBanana MCP Server: inspired by the nano-banana naming convention used across the MCP community. This is an independent implementation.\n- VEO 3.1 by Google DeepMind\n\n## Support\n\nIf you find this useful, please star this repository!\n\n---\n\nMade with ❤️ in the Eastern Province of Saudi Arabia.\n", "bytes": 9587, "sha": "7dcf3a78486f2624daa7dd004563fb9fa58add461aae6c31d6d566811502950d", "repo_slug": "u2n4/gemini-media-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_u2n4_veo_mcp_server_0836bc5d/readme" }