Image Processing MCP Server

Instructions

Implementation Reference

• tools/basic.py:276-333 (handler)

  Core handler function implementing the image format conversion logic using ImageProcessor, including validation, processing, and JSON response.

  async def convert_format(image_source: str, target_format: str, quality: int = 95) -> list[TextContent]:
      """
      转换图片格式
      
      Args:
          image_source: 图片源（文件路径或base64编码数据）
          target_format: 目标格式
          quality: 图片质量
          
      Returns:
          转换后的图片文件引用
      """
      try:
          # 验证参数
          if not image_source or not target_format:
              raise ValidationError("图片源和目标格式不能为空")
          
          if not validate_image_format(target_format):
              raise ValidationError(f"不支持的目标格式: {target_format}")
          
          if not (1 <= quality <= 100):
              raise ValidationError("图片质量必须在1-100之间")
          
          # 加载图片
          image = processor.load_image(image_source)
          
          # 获取原始格式
          original_format = image.format or 'PNG'
          
          # 输出转换后的图片
          output_info = processor.output_image(image, f"convert_to_{target_format.lower()}", target_format, quality)
          
          result = {
              "success": True,
              "message": f"图片格式转换成功: {original_format} -> {target_format}",
              "data": {
                  **output_info,
                  "original_format": original_format,
                  "target_format": target_format,
                  "quality": quality
              }
          }
          
          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"格式转换失败: {str(e)}"
          }
          return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]

• main.py:152-167 (registration)

  MCP tool registration using @mcp.tool() decorator, defining input parameters with descriptions and constraints, and delegating to the basic handler.

  @mcp.tool()
  def convert_format(
      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")],
      target_format: Annotated[str, Field(description="目标格式：PNG、JPEG、WEBP、BMP、TIFF、GIF 等")],
      quality: Annotated[int, Field(description="图片质量，范围 1-100，仅对 JPEG 格式有效", ge=1, le=100, default=95)]
  ) -> str:
      """转换图片格式"""
      try:
          result = safe_run_async(basic_convert_format(image_source, target_format, quality))
          return result[0].text
      except Exception as e:
          return json.dumps({
              "success": False,
              "error": f"转换图片格式失败: {str(e)}"
          }, ensure_ascii=False, indent=2)

• tools/basic.py:70-94 (schema)

  Input schema definition for the convert_format tool within the Tool object returned by get_basic_tools(). Note: actual registration uses Annotated fields in main.py.

  Tool(
      name="convert_format",
      description="转换图片格式",
      inputSchema={
          "type": "object",
          "properties": {
              "image_data": {
                  "type": "string",
                  "description": "图片数据（base64编码）"
              },
              "target_format": {
                  "type": "string",
                  "description": "目标格式（PNG, JPEG, BMP, TIFF, WEBP）"
              },
              "quality": {
                  "type": "integer",
                  "description": "图片质量（1-100，仅对JPEG有效）",
                  "minimum": 1,
                  "maximum": 100,
                  "default": 95
              }
          },
          "required": ["image_data", "target_format"]
      }
  )