Mcp Image

shinpr/mcp-image

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.

GitHub stars: 187
tool: 1
auth: Secret needed
transport: STDIO
env vars: 7
last updated: Nov 5, 2026

View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

generate_imageImage description or editing instruction, with options for quality, provider, input images, aspect ratio and more.

Image description or editing instruction, with options for quality, provider, input images, aspect ratio and more.

No parameter schema in public metadata yet.

Configuration

IMAGE_PROVIDER

Image provider to use: 'gemini' (default), 'openai', or 'seedream'

GEMINI_API_KEYsecret

Google Gemini API key for image generation when IMAGE_PROVIDER=gemini (get from https://aistudio.google.com/apikey)

OPENAI_API_KEYsecret

OpenAI API key for image generation when IMAGE_PROVIDER=openai. Requires OpenAI organization verification to access GPT Image 2.6 (https://platform.openai.com/settings/organization/general)

ARK_API_KEYsecret

BytePlus ModelArk AP region API key required when IMAGE_PROVIDER=seedream

IMAGE_OUTPUT_DIR

Absolute or working-directory-relative path where generated images will be saved (defaults to ./output)

IMAGE_QUALITY

Default quality preset: 'fast' (default), 'balanced', or 'quality'

SKIP_PROMPT_ENHANCEMENT

Set to 'true' to disable automatic prompt optimization and use direct prompts

Readme

MCP Image Generator 🍌

Generate and edit images from Codex, Cursor, Claude Code, or any MCP client. mcp-image adds visual direction to your request before sending it to Gemini, OpenAI, or BytePlus Seedream.

Tell it what image to create or what to change in an existing image, and what it is for. The result is saved to disk and returned to your assistant.

What It Does

Before generating an image, mcp-image rewrites short requests into more specific prompts. It keeps what you asked for and fills in what the image needs for its use, such as lighting and camera angle for a photo or layout for a poster. Text you want in the image stays as you wrote it, in your language. The more detail you provide, the less it changes.

You ask:

View the full README on GitHub

Details

Repository: github.com/shinpr/mcp-image
Category: AI & LLM Tools
Package: mcp-image
Transport: STDIO
Auth: Required
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Codegraphcodegraph-ai/codegraphSemantic code graph: 42 tools, 38 languages. Callers, impact, AI context, memory, PR review.144stars

Shellwardjnmetacode/shellwardAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.108stars

Docs Mcpfrumu-ai/tandemRemote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.107stars

Pensyvemajor7apps/pensyveUniversal memory runtime for AI agents — episodic, semantic, and procedural memory.99stars

emem, the verifiable memory protocol for the physical worldvortx-ai/ememShared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.89stars

Sverklosverklo/sverkloLocal-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.71stars