Skip to main content
Glama
duke0317

Image Processing MCP Server

by duke0317

adjust_contrast

Modify image contrast by adjusting the factor value to enhance or reduce visual clarity and detail visibility in images.

Instructions

调整图片对比度

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
factorYes对比度调整因子,1.0为原始对比度,>1.0增强,<1.0减弱

Implementation Reference

  • Core handler function that loads the image, applies contrast enhancement using PIL ImageEnhance.Contrast, generates output image data, and returns JSON result.
    async def adjust_contrast(image_source: str, factor: float) -> list[TextContent]:
        """
        调整图片对比度
        
        Args:
            image_source: 图片数据(base64编码)或文件路径
            factor: 对比度调整因子(0.0-2.0)
            
        Returns:
            调整后的图片数据
        """
        try:
            # 验证参数
            if not image_source:
                raise ValidationError("图片数据或路径不能为空")
            
            if not validate_numeric_range(factor, 0.0, 2.0):
                raise ValidationError(f"对比度因子必须在0.0-2.0范围内: {factor}")
            
            # 加载图片
            image = processor.load_image(image_source)
            
            # 调整对比度
            enhancer = ImageEnhance.Contrast(image)
            enhanced_image = enhancer.enhance(factor)
            
            # 输出处理后的图片
            output_info = processor.output_image(enhanced_image, "contrast")
            
            result = {
                "success": True,
                "message": f"对比度调整成功: 因子 {factor}",
                "data": {
                    **output_info,
                    "contrast_factor": factor,
                    "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"对比度调整失败: {str(e)}"
            }
            return [TextContent(type="text", text=json.dumps(error_result, ensure_ascii=False))]
  • main.py:399-412 (registration)
    MCP tool registration decorator @mcp.tool() that wraps the handler, provides input schema via Annotated Fields, and handles execution with safe_run_async.
    @mcp.tool()
    def adjust_contrast(
        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")],
        factor: Annotated[float, Field(description="对比度调整因子,1.0为原始对比度,>1.0增强,<1.0减弱", gt=0)]
    ) -> str:
        """调整图片对比度"""
        try:
            result = safe_run_async(color_adjust_contrast(image_source, factor))
            return result[0].text
        except Exception as e:
            return json.dumps({
                "success": False,
                "error": f"调整对比度失败: {str(e)}"
            }, ensure_ascii=False, indent=2)
  • Explicit JSON schema definition for the adjust_contrast tool input, including properties, descriptions, and validation constraints (min/max for factor). Used in get_color_adjust_tools().
    Tool(
        name="adjust_contrast",
        description="调整图片对比度",
        inputSchema={
            "type": "object",
            "properties": {
                "image_source": {
                    "type": "string",
                    "description": "图片数据(base64编码)或文件路径"
                },
                "factor": {
                    "type": "number",
                    "description": "对比度调整因子(0.0-2.0,1.0为原始对比度)",
                    "minimum": 0.0,
                    "maximum": 2.0
                }
            },
            "required": ["image_source", "factor"]
        }
    ),

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