Skip to main content
Glama
IncomeStreamSurfer

OpenAI Image Generation MCP Server

OpenAI 图像生成 MCP 服务器

该项目实现了一个 MCP(模型上下文协议)服务器,该服务器通过官方 Python SDK 提供使用 OpenAI 的gpt-image-1模型生成和编辑图像的工具。

特征

该 MCP 服务器提供以下工具:

  • generate_image :根据文本提示,使用 OpenAI 的gpt-image-1模型生成图像并保存。

    • 输入模式:

      {
        "type": "object",
        "properties": {
          "prompt": { "type": "string", "description": "The text description of the desired image(s)." },
          "model": { "type": "string", "default": "gpt-image-1", "description": "The model to use (currently 'gpt-image-1')." },
          "n": { "type": ["integer", "null"], "default": 1, "description": "The number of images to generate (Default: 1)." },
          "size": { "type": ["string", "null"], "enum": ["1024x1024", "1536x1024", "1024x1536", "auto"], "default": "auto", "description": "Image dimensions ('1024x1024', '1536x1024', '1024x1536', 'auto'). Default: 'auto'." },
          "quality": { "type": ["string", "null"], "enum": ["low", "medium", "high", "auto"], "default": "auto", "description": "Rendering quality ('low', 'medium', 'high', 'auto'). Default: 'auto'." },
          "user": { "type": ["string", "null"], "default": null, "description": "An optional unique identifier representing your end-user." },
          "save_filename": { "type": ["string", "null"], "default": null, "description": "Optional filename (without extension). If None, a default name based on the prompt and timestamp is used." }
        },
        "required": ["prompt"]
      }
    • 输出: {"status": "success", "saved_path": "path/to/image.png"}或错误字典。

  • edit_image :使用 OpenAI 的gpt-image-1模型编辑图像或创建变体并保存。可以使用多张输入图像作为参考,或使用遮罩进行修复。

    • 输入模式:

      {
        "type": "object",
        "properties": {
          "prompt": { "type": "string", "description": "The text description of the desired final image or edit." },
          "image_paths": { "type": "array", "items": { "type": "string" }, "description": "A list of file paths to the input image(s). Must be PNG. < 25MB." },
          "mask_path": { "type": ["string", "null"], "default": null, "description": "Optional file path to the mask image (PNG with alpha channel) for inpainting. Must be same size as input image(s). < 25MB." },
          "model": { "type": "string", "default": "gpt-image-1", "description": "The model to use (currently 'gpt-image-1')." },
          "n": { "type": ["integer", "null"], "default": 1, "description": "The number of images to generate (Default: 1)." },
          "size": { "type": ["string", "null"], "enum": ["1024x1024", "1536x1024", "1024x1536", "auto"], "default": "auto", "description": "Image dimensions ('1024x1024', '1536x1024', '1024x1536', 'auto'). Default: 'auto'." },
          "quality": { "type": ["string", "null"], "enum": ["low", "medium", "high", "auto"], "default": "auto", "description": "Rendering quality ('low', 'medium', 'high', 'auto'). Default: 'auto'." },
          "user": { "type": ["string", "null"], "default": null, "description": "An optional unique identifier representing your end-user." },
          "save_filename": { "type": ["string", "null"], "default": null, "description": "Optional filename (without extension). If None, a default name based on the prompt and timestamp is used." }
        },
        "required": ["prompt", "image_paths"]
      }
    • 输出: {"status": "success", "saved_path": "path/to/image.png"}或错误字典。

Related MCP server: imagengen

先决条件

  • Python(建议使用 3.8 或更高版本)

  • pip(Python 包安装程序)

  • OpenAI API 密钥(直接在脚本中设置或通过OPENAI_API_KEY环境变量设置 -强烈建议使用环境变量以确保安全)。

  • MCP 客户端环境(如 Cline 使用的环境)能够管理和启动 MCP 服务器。

安装

  1. 克隆存储库:

    git clone https://github.com/IncomeStreamSurfer/chatgpt-native-image-gen-mcp.git
    cd chatgpt-native-image-gen-mcp
  2. 设置虚拟环境(推荐):

    python -m venv venv
    source venv/bin/activate  # On Windows use `venv\Scripts\activate`
  3. 安装依赖项:

    pip install -r requirements.txt
  4. **(可选但推荐)设置环境变量:**使用您的 OpenAI 密钥设置OPENAI_API_KEY环境变量,而不是将其硬编码在脚本中。如何设置取决于您的操作系统。

配置(适用于 Cline MCP 客户端)

为了使您的 AI 助手(如 Cline)可以使用此服务器,请将其配置添加到您的 MCP 设置文件(例如, cline_mcp_settings.json )。

在您的设置文件中找到mcpServers对象并添加以下条目:

{
  "mcpServers": {
    // ... other server configurations ...

    "openai-image-gen-mcp": {
      "autoApprove": [
        "generate_image",
        "edit_image"
      ],
      "disabled": false,
      "timeout": 180, // Increased timeout for potentially long image generation
      "command": "python", // Or path to python executable if not in PATH
      "args": [
        // IMPORTANT: Replace this path with the actual absolute path
        // to the openai_image_mcp.py file on your system
        "C:/path/to/your/cloned/repo/chatgpt-native-image-gen-mcp/openai_image_mcp.py"
      ],
      "env": {
        // If using environment variables for the API key:
        // "OPENAI_API_KEY": "YOUR_API_KEY_HERE"
      },
      "transportType": "stdio"
    }

    // ... other server configurations ...
  }
}

**重要提示:**请将C:/path/to/your/cloned/repo/替换为您在计算机上克隆此仓库的正确绝对路径。请确保路径分隔符与您的操作系统匹配(例如,在 Windows 上使用反斜杠\ )。如果您通过环境变量设置了 API 密钥,则可以将其从脚本中移除,并在您的 MCP 客户端支持的情况下将其添加到此处的env部分。

运行服务器

通常情况下,您无需手动运行服务器。MCP 客户端(例如 Cline)会在首次调用其工具时,使用配置文件中指定的commandargs自动启动服务器。

如果您想手动测试它(确保依赖项已安装并且 API 密钥可用):

python openai_image_mcp.py

用法

AI 助手使用generate_imageedit_image工具与服务器交互。图像保存在openai_image_mcp.py脚本所在位置的ai-images子目录中。成功后,这两个工具会返回已保存图像的绝对路径。

Related MCP Connectors

Related MCP Servers