Gemini Image Generation MCP Server

@sanxfxteam

关于 Gemini Image Generation MCP Server

Generate images using gemini

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "gemini-mcp-server-sanxfxteam": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "npm",
        "run",
        "start"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Gemini Image Generation MCP Server?

It is a Model Context Protocol (MCP) server that provides image generation capabilities using Google's Gemini 2 API. Designed for developers and Claude Desktop users who want to generate images directly from MCP-compatible tools.

How to use Gemini Image Generation MCP Server?

Obtain a Gemini API key from Google AI Studio, then configure Claude Desktop by adding the server entry to its config file with the GEMINI_API_KEY environment variable. Restart Claude Desktop and invoke the generateImage tool with a required prompt and optional parameters (numSamples, aspectRatio, personGeneration). Alternatively, run the server locally with npm start.

Key features of Gemini Image Generation MCP Server

Generates images using Gemini 2’s experimental image generation API
Provides a single generateImage tool with required prompt
Supports configurable number of samples (default 4)
Supports aspect ratio options (default 1:1)
Supports person generation settings (default ALLOW_ADULT)

Use cases of Gemini Image Generation MCP Server

Generate custom visuals directly from Claude Desktop using natural language prompts
Quickly produce multiple image variations for content or design ideas
Integrate image generation into MCP‑based workflows or automation

FAQ from Gemini Image Generation MCP Server

What does this server do?

It acts as an MCP-compatible bridge that sends image generation requests to Google’s Gemini 2 experimental API and returns the resulting images.

What are the runtime requirements?

You need Node.js, npm, a valid Google Gemini API key, and an internet connection. The server runs over stdio via the MCP transport.

Where does generated image data live?

Images are generated remotely by Google’s Gemini API; the server only passes requests and responses. No persistent storage is handled by the server.

Is the image generation feature stable?

The server uses the experimental image generation feature of Gemini 2, so behavior may change. Ensure you have appropriate API access from Google.

How is authentication handled?

Authentication is done via a GEMINI_API_KEY environment variable set in the MCP server configuration or in a .env file.

常见问题

What does this server do?

It acts as an MCP-compatible bridge that sends image generation requests to Google’s Gemini 2 experimental API and returns the resulting images.

What are the runtime requirements?

You need Node.js, npm, a valid Google Gemini API key, and an internet connection. The server runs over stdio via the MCP transport.

Where does generated image data live?

Images are generated remotely by Google’s Gemini API; the server only passes requests and responses. No persistent storage is handled by the server.

Is the image generation feature stable?

The server uses the **experimental** image generation feature of Gemini 2, so behavior may change. Ensure you have appropriate API access from Google.

How is authentication handled?

Authentication is done via a `GEMINI_API_KEY` environment variable set in the MCP server configuration or in a `.env` file.

基本信息

分类

AI 与智能体

许可证

MIT

传输方式

stdio

作者

sanxfxteam

AI 与智能体分类下的更多 MCP 服务器

Lumify Sports Intelligence

Lumify

Agent-ready sports intelligence API: live scores, odds, line movement, public betting splits, and explainable bet confidence — via 16 MCP tools at https://lumify.ai/mcp. Get a free key instantly — no signup, email, or ca

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei