organon-create-image
MCP server for generating images using Gemini, supporting multiple aspect ratios and both AI Studio and Vertex AI backends.
README
organon-create-image
MCP server for image generation using Gemini.
Features
- Text-to-image generation via Gemini (default:
gemini-3-pro-image-preview) - Multiple aspect ratio support (1:1, 16:9, 9:16, etc.)
- Returns generated images both as files and inline via MCP image content type
- Supports both AI Studio (API key) and Vertex AI (service account) backends
Prerequisites
- Node.js 18+
- One of the following:
- AI Studio: A Gemini API key from Google AI Studio
- Vertex AI: A Google Cloud project with Vertex AI API enabled + Application Default Credentials
Setup
npm install
npm run build
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GEMINI_API_KEY |
Option 1 | — | AI Studio API key (takes priority over Vertex AI) |
VERTEX_PROJECT |
Option 2 | — | Google Cloud project ID (Vertex AI) |
VERTEX_LOCATION |
No | us-central1 |
Vertex AI location |
Note: Set either
GEMINI_API_KEYorVERTEX_PROJECT. If both are set,GEMINI_API_KEYtakes priority.
Claude Code MCP Registration
AI Studio (recommended for access to preview models):
{
"mcpServers": {
"create-image": {
"command": "node",
"args": ["/path/to/organon-create-image/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key"
}
}
}
}
Vertex AI:
{
"mcpServers": {
"create-image": {
"command": "node",
"args": ["/path/to/organon-create-image/dist/index.js"],
"env": {
"VERTEX_PROJECT": "your-gcp-project-id"
}
}
}
}
Tools
generate_image
Generate an image from a text prompt.
Parameters:
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | Yes | — | Text prompt for image generation (English recommended) |
aspect_ratio |
enum | No | "1:1" |
Aspect ratio: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
output_path |
string | Yes | — | File path to save the generated image (.png) |
model |
string | No | "gemini-3-pro-image-preview" |
Gemini model name (e.g. gemini-2.5-flash-image) |
Returns: Generated image saved to output_path, plus inline image via MCP image content type.
Quality Checks
Run all quality checks at once:
npm run check:all
This executes the following checks in sequence:
| Script | Check | Tool |
|---|---|---|
typecheck |
Type checking (strict) | tsc --noEmit |
lint |
Linter + cyclomatic complexity | ESLint + typescript-eslint |
format:check |
Code formatting | Prettier |
test:coverage |
Tests + coverage report | Vitest + V8 |
audit |
Known CVE scan | npm audit |
audit:lockfile |
Lockfile integrity | lockfile-lint |
sast |
Security static analysis | Semgrep |
Note: Semgrep requires a separate installation via
pip. See QUALITY.md for setup details.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。