mcp-image
Active·★ 181·MIT·Updated 2026-10-21
★ Hidden Gem
mcp-image is a tool for generating and editing images, integrating with MCP clients like Codex, Cursor, and Claude Code. It intelligently rewrites short image requests into more specific prompts, enhancing details like composition and lighting before sending them to various AI image models such as Gemini, OpenAI, and BytePlus Seedream.
#Image Generation#Prompt Enhancement#Image Editing#Multi-Agent Client (MCP)#AI Models#Node.js#Developer Tooling
01
Features
01Prompt Enhancement: Automatically rewrites short requests into detailed prompts, adding composition, lighting, and camera angle specifics.
02Multi-Provider Support: Integrates with Gemini, OpenAI, and BytePlus Seedream for image generation and editing.
03Image Editing: Supports modifying existing images based on textual instructions.
04MCP Client Integration: Seamlessly works with Codex, Cursor, and Claude Code clients.
05Configurable Quality & Output: Allows setting image quality presets (fast, balanced, quality) and output directories.
02
Compatibility
Node.js
Runtime
Verified via docs
MCP Client
Client
Verified via docs
Gemini API
Image Provider
Verified via docs
OpenAI API
Image Provider
Verified via docs
BytePlus Seedream API
Image Provider
Verified via docs
03
Quick start
1
$ npx -y mcp-image
04
Use cases
↳Generating product photos for e-commerce or marketing.
↳Creating visual assets for recipe sites or blogs with specific details.
↳Editing existing images to change elements or composition.
↳Developing visual content for social media or presentations with enhanced prompts.
↳Rapid prototyping of visual ideas with different quality settings.
05
Alternatives
ai-doc-gen★ 768
AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.
gemini-webapi-mcp★ 63
MCP server for Google Gemini — free image generation, editing & chat via browser cookies. No API keys needed.
comfyui-mcp★ 853
Claude Code plugin + MCP server for ComfyUI — 88 tools, 14 AI skills (Flux, WAN, LTX video, Qwen), live graph editing from your Claude session. Generate images & video, manage models and custom nodes.
blender-plugin★ 568
Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.
mcp-screenshot-website-fast★ 110
Quickly screenshots webpages and converts to an LLM friendly size
kreuzberg★ 9.4k
A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 50+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.
Comments
Log in to leave a comment
No comments yet. Be the first!