What do I need to run this server?
You need Node.js 18 or higher and a Google API key with access to the Gemini API (specifically the image generation preview model). Docker is optional but supported.
@collactivelabs
Basic information
A Model Calling Protocol (MCP) server that allows Claude and other LLMs to generate images using Google's Gemini AI model.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"openai-image-generation": {
"command": "node",
"args": [
"/full/path/to/openai-image-gen-mcp/src/mcp-server.js"
],
"env": {
"OPENAI_API_KEY": "your-openai-api-key-here"
}
}
}
}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.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Gemini Image Generation MCP is an MCP server that enables LLMs like Claude to generate images using Google's Gemini AI model (gemini-2.0-flash-preview-image-generation). It saves generated images locally and includes an interactive web interface for testing and demonstration.
Install Node.js 18+, clone the repository, install dependencies (npm install), and set your GEMINI_API_KEY in the .env file. Run the MCP server with node src/mcp-server.js or use Docker. Configure Claude or another MCP client to connect via the MCP protocol—either through JSON configuration or the Claude console’s MCPs section.
You need Node.js 18 or higher and a Google API key with access to the Gemini API (specifically the image generation preview model). Docker is optional but supported.
Create a `.env` file from `.env.example` and set `GEMINI_API_KEY` (required). Optional settings include `MCP_AUTH_TOKEN`, `PORT`, `OUTPUT_DIR`, and `LOG_LEVEL`.
You can add the MCP server configuration in Claude’s settings via JSON or through the Claude console’s MCPs section, specifying the server URL and any authentication token.
By default, images are saved in the `./generated-images` directory, configurable via the `OUTPUT_DIR` environment variable.
The server uses the `gemini-2.0-flash-preview-image-generation` model, which is optimized for image generation tasks.
28-tool MCP server for web scraping, crawling, deep research & autonomous extraction — clean Markdown & structured JSON for Claude, Cursor & any MCP client. 1,000 free one-time credits, local-Ollama LLM support.
Cartesia MCP is a remote MCP server for Cartesia (https://cartesia.ai) available at https://mcp.cartesia.ai.

Quantum-inspired keyring for AI coding agents. Secure secrets with superposition, entanglement, tunneling, and teleportation — CLI + 44 MCP tools.

Free MCP server for dating profiles. Look up the official photo rules and AI-photo policies of Tinder, Hinge and Bumble — photo limits, verification, what gets you banned — each quoted from the app's own guidelines wi
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi
Comments