Image Processing MCP Server

Instructions

Implementation Reference

• tools/filters.py:234-287 (handler)

  Core handler function implementing the Gaussian blur effect: validates inputs, loads image from base64 data, applies PIL's ImageFilter.GaussianBlur(radius), processes output via ImageProcessor, returns JSON result as TextContent list.

  async def apply_gaussian_blur(image_data: str, radius: float) -> list[TextContent]:
      """
      应用高斯模糊滤镜
      
      Args:
          image_data: 图片数据（base64编码）
          radius: 高斯模糊半径
          
      Returns:
          应用滤镜后的图片数据
      """
      try:
          # 验证参数
          if not image_data:
              raise ValidationError("图片数据不能为空")
          
          if not validate_numeric_range(radius, 0.1, 10.0):
              raise ValidationError(f"高斯模糊半径必须在0.1-10.0范围内: {radius}")
          
          # 加载图片
          image = processor.load_image(image_data)
          
          # 应用高斯模糊滤镜
          blurred_image = image.filter(ImageFilter.GaussianBlur(radius))
          
          # 输出处理后的图片
          output_info = processor.output_image(blurred_image, "gaussian_blur")
          
          result = {
              "success": True,
              "message": f"高斯模糊滤镜应用成功: 半径 {radius}",
              "data": {
                  **output_info,
                  "filter_type": "gaussian_blur",
                  "radius": radius,
                  "size": image.size
              }
          }
          
          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"高斯模糊滤镜应用失败: {str(e)}"
          }
          return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]

• main.py:255-269 (registration)

  MCP tool registration using @mcp.tool() decorator. Defines input schema via Annotated[Field] for image_source and radius parameters. Delegates execution to the filters.py handler via safe_run_async with error handling and JSON response formatting.

  @mcp.tool()
  def apply_gaussian_blur(
      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")],
      radius: Annotated[float, Field(description="高斯模糊半径，值越大模糊效果越强", ge=0.1)]
  ) -> str:
      """应用高斯模糊滤镜"""
      try:
          result = safe_run_async(filters_apply_gaussian_blur(image_source, radius))
          return result[0].text
      except Exception as e:
          return json.dumps({
              "success": False,
              "error": f"应用高斯模糊失败: {str(e)}"
          }, ensure_ascii=False, indent=2)

• tools/filters.py:45-64 (schema)

  Tool schema definition within get_filter_tools(), specifying JSON schema for inputs: image_data (base64 string) and radius (number 0.1-10.0). Note: This appears unused in the main registration flow.

  Tool(
      name="apply_gaussian_blur",
      description="应用高斯模糊滤镜",
      inputSchema={
          "type": "object",
          "properties": {
              "image_data": {
                  "type": "string",
                  "description": "图片数据（base64编码）"
              },
              "radius": {
                  "type": "number",
                  "description": "高斯模糊半径（0.1-10.0）",
                  "minimum": 0.1,
                  "maximum": 10.0
              }
          },
          "required": ["image_data", "radius"]
      }
  ),