Gemini Flash MCP
by jezweb
This MCP server connects to Google's Gemini 2.0 Flash for image generation, designed for Roo Code and other MCP-compatible AI assistants. It allows AI assistants to generate images through the Model Context Protocol (MCP) with fine-grained control over the generation process.
Last updated: N/A
What is Gemini Flash MCP?
This is a Model Context Protocol (MCP) server that enables image generation using Google's Gemini 2.0 Flash model. It allows AI assistants like Roo Code to generate images with comprehensive support for available API options.
How to use Gemini Flash MCP?
To use, install the server globally or manually following the provided instructions. Configure your Google AI API key and integrate the server with Roo Code or Claude Desktop using the MCP settings. Once configured, use the generate_image tool with appropriate parameters like prompt, temperature, topP, topK, and maxOutputTokens.
Key features of Gemini Flash MCP
Text-to-image generation using Google's Gemini 2.0 Flash model
Full support for all available API parameters
Simple web interface for testing and demonstration
Easy installation for Roo Code and Claude Desktop
Comprehensive documentation and examples
Use cases of Gemini Flash MCP
Generating images from text prompts within AI assistants
Creating visual content for applications and websites
Prototyping image ideas quickly
Integrating image generation into automated workflows
FAQ from Gemini Flash MCP
How do I resolve API key issues?
How do I resolve API key issues?
Verify your API key is correct, ensure you have access to the Gemini 2.0 Flash model, and check that the environment variable is properly set in your MCP configuration.
What should I do if the MCP server fails to connect?
What should I do if the MCP server fails to connect?
Check that the server is running, verify the path in your MCP configuration is correct, and ensure the server has the correct permissions.
What parameters are available for the generate_image tool?
What parameters are available for the generate_image tool?
The tool supports parameters like prompt (required), temperature, topP, topK, and maxOutputTokens.
How do I test the image generation?
How do I test the image generation?
A web interface is available. Run npm start and open your browser to http://localhost:3000.
Where can I find the source code?
Where can I find the source code?
The source code is located in the src/ directory, with the main server file at src/index.ts.