Skip to main content
Glama
duke0317

Image Processing MCP Server

by duke0317

apply_emboss

Adds a 3D embossed effect to images by applying a filter that creates raised or engraved appearance for visual enhancement.

Instructions

应用浮雕滤镜

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
image_sourceYes图片源,可以是文件路径或base64编码的图片数据

Implementation Reference

  • Core handler function that loads the image, applies PIL's ImageFilter.EMBOSS filter, processes output via ImageProcessor, and returns JSON result as TextContent.
    async def apply_emboss(image_data: str) -> list[TextContent]:
        """
        应用浮雕滤镜
        
        Args:
            image_data: 图片数据(base64编码)
            
        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")
            
            # 加载图片
            image = processor.load_image(image_data)
            
            # 应用浮雕滤镜
            embossed_image = image.filter(ImageFilter.EMBOSS)
            
            # 输出处理后的图片
            output_info = processor.output_image(embossed_image, "emboss")
            
            result = {
                "success": True,
                "message": "浮雕滤镜应用成功",
                "data": {
                    **output_info,
                    "filter_type": "emboss",
                    "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"浮雕滤镜应用失败: {str(e)}"
            }
            return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]
  • main.py:299-310 (registration)
    MCP tool registration via @mcp.tool() decorator. This wrapper function delegates to the filters.apply_emboss handler using safe_run_async.
    def apply_emboss(
        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:
        """应用浮雕滤镜"""
        try:
            result = safe_run_async(filters_apply_emboss(image_source))
            return result[0].text
        except Exception as e:
            return json.dumps({
                "success": False,
                "error": f"应用浮雕效果失败: {str(e)}"
            }, ensure_ascii=False, indent=2)
  • Tool schema definition in get_filter_tools(), specifying input schema for 'image_data' parameter, though primarily used via main.py decorator.
    Tool(
        name="apply_emboss",
        description="应用浮雕滤镜",
        inputSchema={
            "type": "object",
            "properties": {
                "image_data": {
                    "type": "string",
                    "description": "图片数据(base64编码)"
                }
            },
            "required": ["image_data"]
        }
    ),

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/duke0317/ps-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server