Image Processing MCP Server

Instructions

Implementation Reference

• tools/basic.py:214-274 (handler)

  Core asynchronous handler function that implements the get_image_info tool logic: validates input, loads image using ImageProcessor, retrieves basic info, computes extended metrics (data size, aspect ratio, pixels, file info), and returns formatted JSON response.

  async def get_image_info(image_source: str) -> list[TextContent]:
      """
      获取图片信息
      
      Args:
          image_source: 图片源（文件路径或base64编码数据）
          
      Returns:
          图片信息响应
      """
      try:
          # 验证参数
          if not image_source:
              raise ValidationError("图片源不能为空")
          
          # 加载图片
          image = processor.load_image(image_source)
          
          # 获取详细信息
          info = processor.get_image_info(image)
          
          # 计算图片大小（字节）
          import io
          buffer = io.BytesIO()
          image.save(buffer, format=image.format or 'PNG')
          data_size = len(buffer.getvalue())
          
          # 扩展信息
          extended_info = {
              **info,
              "data_size": data_size,
              "aspect_ratio": round(info['width'] / info['height'], 2),
              "total_pixels": info['width'] * info['height']
          }
          
          # 如果是文件路径，添加文件信息
          if not image_source.startswith('data:image') and os.path.exists(image_source):
              extended_info["file_path"] = image_source
              extended_info["file_size_bytes"] = os.path.getsize(image_source)
          
          result = {
              "success": True,
              "message": "获取图片信息成功",
              "data": extended_info
          }
          
          return [TextContent(type="text", text=json.dumps(result, ensure_ascii=False))]
          
      except ValidationError as e:
          error_result = {
              "success": False,
              "error": f"参数验证失败: {str(e)}"
          }
          return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]
          
      except Exception as e:
          error_result = {
              "success": False,
              "error": f"获取图片信息失败: {str(e)}"
          }
          return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]

• main.py:138-151 (registration)

  FastMCP tool registration decorator (@mcp.tool()) that defines the public tool interface, calls the core handler via safe_run_async, and handles errors by returning JSON.

  @mcp.tool()
  def get_image_info(
      image_source: Annotated[str, Field(description="图片源，可以是文件路径或base64编码的图片数据")]
  ) -> str:
      """获取图片基本信息"""
      try:
          result = safe_run_async(basic_get_image_info(image_source))
          return result[0].text
      except Exception as e:
          return json.dumps({
              "success": False,
              "error": f"获取图片信息失败: {str(e)}"
          }, ensure_ascii=False, indent=2)

• tools/basic.py:56-69 (schema)

  Tool schema definition in get_basic_tools() function, specifying input requirements (image_data as base64 string) and description for the get_image_info tool.

  Tool(
      name="get_image_info",
      description="获取图片基本信息",
      inputSchema={
          "type": "object",
          "properties": {
              "image_data": {
                  "type": "string",
                  "description": "图片数据（base64编码）"
              }
          },
          "required": ["image_data"]
      }
  ),

• utils/image_processor.py:129-146 (helper)

  Supporting utility method in ImageProcessor class that extracts basic PIL Image properties (size, mode, format, dimensions) used by the main handler.

  def get_image_info(self, image: Image.Image) -> dict:
      """
      获取图片信息
      
      Args:
          image: PIL Image对象
          
      Returns:
          包含图片信息的字典
      """
      return {
          'size': image.size,
          'mode': image.mode,
          'format': image.format,
          'width': image.width,
          'height': image.height
      }