Gemini Image Generation MCP
@collactivelabs
About Gemini Image Generation MCP
A Model Calling Protocol (MCP) server that allows Claude and other LLMs to generate images using Google's Gemini AI model.
Basic information
Config
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"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Gemini Image Generation MCP?
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.
How to use Gemini Image Generation MCP?
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.
Key features of Gemini Image Generation MCP
- Generate images from text prompts using Google’s Gemini model.
- Save generated images locally.
- Configure generation parameters like temperature, topK, and topP.
- Interactive web interface for testing and demonstration.
- Docker support for easy deployment.
- Simple MCP standard implementation.
Use cases of Gemini Image Generation MCP
- Enable Claude to generate images as part of conversations.
- Automate image creation for content generation pipelines.
- Test and demo Gemini image generation capabilities via the web interface.
- Integrate image generation into custom applications using the MCP protocol.
FAQ from Gemini Image Generation MCP
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.
How do I configure the server?
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.
How does the server integrate with Claude?
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.
Where are generated images saved?
By default, images are saved in the ./generated-images directory, configurable via the OUTPUT_DIR environment variable.
What Gemini model is used for generation?
The server uses the gemini-2.0-flash-preview-image-generation model, which is optimized for image generation tasks.
More AI & Agents MCP servers
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
Comments