gemini_prompt_assistant
Expert guidance for image generation with 9 chart design systems
How to use it
Project documentation lists gemini_prompt_assistant for the Gemini MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Gemini MCP
claude mcp add -e GEMINI_API_KEY=your-api-key-here -s user gemini -- npx -y @houtini/gemini-mcpOther tools in Gemini MCP (12)
Structured extraction and analysis using Gemini 3.1 Pro
Fast image descriptions using Gemini 3 Flash
Edit images with natural-language instructions. Multi-turn continuity via thought signatures
Chat with Gemini 3.1 Pro. Google Search grounding on by default. Supports thinkinglevel
Multi-step iterative research with Google Search. Synthesises comprehensive reports
Documentation for all features without leaving Claude
Lists available models from the Gemini API
Image generation with optional search grounding. Full-res saved to disk
Self-contained HTML landing pages with inline CSS/JS
Production-ready SVG: diagrams, illustrations, icons, data visualisations
Video generation with Veo 3.1 — 4-8 seconds at up to 4K with native audio
Read a local image file and return base64 for any image tool