mcp-image

MCP ServerMCP Registry官方收录

io.github.shinpr/mcp-image · v0.11.2

AI image generation and editing with prompt optimization and quality presets

源仓库 ↗

概览

mcp-image 是一个MCP Server，收录自官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

{
  "mcpServers": {
    "mcp-image": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-image"
      ]
    }
  }
}

环境变量

IMAGE_PROVIDER可选

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

GEMINI_API_KEY可选secret

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

OPENAI_API_KEY可选secret

OpenAI API key for image generation when IMAGE_PROVIDER=openai. Requires OpenAI organization verification to access gpt-image-2 (https://platform.openai.com/settings/organization/general)

IMAGE_OUTPUT_DIR可选

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

IMAGE_QUALITY可选

Default quality preset: 'fast' (Nano Banana 2, default), 'balanced' (Nano Banana 2 + thinking), 'quality' (Nano Banana Pro)

SKIP_PROMPT_ENHANCEMENT可选

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

统一 Manifest

{
  "id": "io.github.shinpr/mcp-image",
  "type": "mcp-server",
  "version": "0.11.2",
  "displayName": "mcp-image",
  "description": "AI image generation and editing with prompt optimization and quality presets",
  "repository": {
    "url": "https://github.com/shinpr/mcp-image",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "npm",
        "identifier": "mcp-image",
        "version": "0.11.2",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "IMAGE_PROVIDER",
            "description": "Image provider to use: 'gemini' (default) or 'openai'"
          },
          {
            "name": "GEMINI_API_KEY",
            "description": "Google Gemini API key for image generation when IMAGE_PROVIDER=gemini (get from https://aistudio.google.com/apikey)",
            "isSecret": true
          },
          {
            "name": "OPENAI_API_KEY",
            "description": "OpenAI API key for image generation when IMAGE_PROVIDER=openai. Requires OpenAI organization verification to access gpt-image-2 (https://platform.openai.com/settings/organization/general)",
            "isSecret": true
          },
          {
            "name": "IMAGE_OUTPUT_DIR",
            "description": "Absolute path to directory where generated images will be saved (defaults to ./output)"
          },
          {
            "name": "IMAGE_QUALITY",
            "description": "Default quality preset: 'fast' (Nano Banana 2, default), 'balanced' (Nano Banana 2 + thinking), 'quality' (Nano Banana Pro)"
          },
          {
            "name": "SKIP_PROMPT_ENHANCEMENT",
            "description": "Set to 'true' to disable automatic prompt optimization and use direct prompts"
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.shinpr/mcp-image",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.shinpr%2Fmcp-image/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}

mcp-image

概览

安装

环境变量

相关资源

RFP.ai

xenarch-mcp

api

agent-lsp

hostinger-api-mcp

Unterm

统一 Manifest