apply_contour
Detect and apply contour effects to an image using the apply_contour tool. Enhance edges and extract outlines by processing image data, supporting input as a file path or base64-encoded string. Ideal for edge detection tasks in image processing workflows.
Instructions
应用轮廓滤镜
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image_source | Yes | 图片源，可以是文件路径或base64编码的图片数据 |
Implementation Reference
- tools/filters.py:539-587 (handler)Core handler function that loads the image using ImageProcessor, applies PIL's ImageFilter.CONTOUR filter, generates output image data, and returns a JSON-formatted result as TextContent.async def apply_contour(image_data: str) -> list[TextContent]: """ 应用轮廓滤镜 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) # 应用轮廓滤镜 contour_image = image.filter(ImageFilter.CONTOUR) # 输出处理后的图片 output_info = processor.output_image(contour_image, "contour") result = { "success": True, "message": "轮廓滤镜应用成功", "data": { **output_info, "filter_type": "contour", "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"轮廓滤镜应用失败: {str(e)}" } return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]
- tools/filters.py:135-148 (schema)Input schema definition for the apply_contour tool within the get_filter_tools() function, specifying base64 image_data as required input.Tool( name="apply_contour", description="应用轮廓滤镜", inputSchema={ "type": "object", "properties": { "image_data": { "type": "string", "description": "图片数据（base64编码）" } }, "required": ["image_data"] } ),
- main.py:340-352 (registration)MCP tool registration via FastMCP's @mcp.tool() decorator. This wrapper function calls the core handler from filters.py and handles errors, with input schema inferred from Annotated Field.@mcp.tool() def apply_contour( 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: """应用轮廓滤镜""" try: result = safe_run_async(filters_apply_contour(image_source)) return result[0].text except Exception as e: return json.dumps({ "success": False, "error": f"应用轮廓效果失败: {str(e)}" }, ensure_ascii=False, indent=2)