XMZ MCP Server

Instructions

Implementation Reference

• src/server.ts:387-398 (handler)

  MCP tool handler function that calls the CIAIInstance.aiPicMatting service method and formats the response.

  async ({ objectKey, width = '5', height = '5' }) => {
    const res = await CIAIInstance.aiPicMatting(objectKey, width, height);
    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(res.data, null, 2),
        },
      ],
      isError: !res.isSuccess,
    };
  },

• src/server.ts:382-386 (schema)

  Zod schema defining input parameters: objectKey (required), width and height (optional).

  {
    objectKey: z.string().describe('图片在存储桶里的路径'),
    width: z.string().optional().describe('宽度'),
    height: z.string().optional().describe('高度'),
  },

• src/server.ts:379-399 (registration)

  Registration of the 'aiPicMatting' tool using McpServer.tool(), including description, schema, and handler.

  server.tool(
    'aiPicMatting',
    '图片处理-抠图',
    {
      objectKey: z.string().describe('图片在存储桶里的路径'),
      width: z.string().optional().describe('宽度'),
      height: z.string().optional().describe('高度'),
    },
    async ({ objectKey, width = '5', height = '5' }) => {
      const res = await CIAIInstance.aiPicMatting(objectKey, width, height);
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(res.data, null, 2),
          },
        ],
        isError: !res.isSuccess,
      };
    },
  );

• src/services/ci/ai.service.ts:90-151 (helper)

  Helper method in CIAIService class that performs the actual AI image matting (抠图) using Tencent COS image_process API with AIImageCrop rule.

  async aiPicMatting(objectKey: string, width: string, height: string) {
    try {
      const result = await new Promise((resolve, reject) => {
        const outPutFileid = generateOutPutFileId(objectKey);
        this.cos.request(
          {
            Bucket: this.bucket, // 存储桶，必须字段
            Region: this.region, // 存储桶所在地域，必须字段 如 ap-beijing
            Key: objectKey, // 对象文件名，例如：folder/document.jpg。
            Method: 'POST', // 固定值
            Action: 'image_process', // 固定值
            Headers: {
              'Pic-Operations': JSON.stringify({
                rules: [
                  {
                    fileid: `${outPutFileid}`,
                    rule:
                      'ci-process=AIImageCrop&width=' +
                      width +
                      '&height=' +
                      height,
                  },
                ],
              }),
            },
          },
          function (error, data) {
            if (error) {
              // 处理请求失败
              reject(error);
            } else {
              // 处理请求成功
              resolve(data);
            }
          },
        );
      });
  
      // const localPath = "结果.png"; // 填写要写入的本地文件路径
      // if (result.Body) {
      //   fs.writeFileSync(localPath, result.Body); // 将图片内容保存本地路径
      // } else {
      //   throw new Error("Result body is undefined");
      // }
      // if (!result.Body) {
      //   throw new Error("Result body is undefined");
      // }
      // const base64Image = `data:image/jpeg;base64,${typeof result.Body === "string" ? Buffer.from(result.Body).toString("base64") : result.Body.toString("base64")}`;
  
      return {
        isSuccess: true,
        message: '图片处理成功',
        data: result,
      };
    } catch (error) {
      return {
        isSuccess: false,
        message: '图片处理失败',
        data: error,
      };
    }
  }