Generates and edits images through Gemini 3 Pro Image (or OpenAI GPT Image with provider flag). Exposes tools for text-to-image and image-to-image operations with built-in prompt optimization that auto-enhances your input using a Subject-Context-Style framework. The server adds lighting, composition, and atmospheric details without requiring prompt engineering skills. Supports quality presets from fast iteration to 4K output, character consistency across generations, and flexible aspect ratios up to 21:9. Includes Google Search grounding for factual accuracy and multi-image blending. Ships with an optional Agent Skill file that teaches assistants prompt techniques for tools with native image generation. Requires Gemini or OpenAI API key and Node.js 22+. Works with Cursor, Claude Code, Codex, and other MCP clients.
claude mcp add --transport stdio shinpr-mcp-image uvx mcp-image