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.
@sanxfxteam
Basic information
Generate images using gemini
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"gemini-mcp-server-sanxfxteam": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"npm",
"run",
"start"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
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.
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.
generateImage tool with required promptIt acts as an MCP-compatible bridge that sends image generation requests to Google’s Gemini 2 experimental API and returns the resulting images.
You need Node.js, npm, a valid Google Gemini API key, and an internet connection. The server runs over stdio via the MCP transport.
Images are generated remotely by Google’s Gemini API; the server only passes requests and responses. No persistent storage is handled by the server.
The server uses the **experimental** image generation feature of Gemini 2, so behavior may change. Ensure you have appropriate API access from Google.
Authentication is done via a `GEMINI_API_KEY` environment variable set in the MCP server configuration or in a `.env` file.
GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,
Model Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app

Krafters is a French club of specialized AIs for freelancers and small businesses. Its connector opens the member's AI kits for Facebook and Instagram ads, SEO/GEO and short videos directly in Claude, and gives the next
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

Search a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.
Comments